Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41304
    Prev
    Next
    INDEX
    Explanations

    I/It

    np_max-act · gemini-2.0-flash

    The neuron detects self-referential, first-person statements — parts where the author expresses personal opinion, experience, or perspective.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝇠
    -0.07
    实事求
    -0.07
    醵
    -0.07
    عقب
    -0.06
     Depart
    -0.06
     الب
    -0.06
    	mp
    -0.06
    _MSB
    -0.06
    擬
    -0.06
     adec
    -0.06
    POSITIVE LOGITS
    Personal
    0.08
    就已经
    0.08
    selection
    0.08
    臉
    0.07
    一页
    0.07
    fin
    0.07
                 
    0.07
     fac
    0.07
    跌幅
    0.07
     fertil
    0.07
    Activations Density 0.051%

    No Known Activations