© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 41096
    Prev
    Next
    INDEX
    Explanations

    .Get

    np_max-act · gemini-2.0-flash
    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
    周四
    -0.07
     пок
    -0.07
     الولا
    -0.07
    Neill
    -0.07
     başında
    -0.07
    电线
    -0.07
    wk
    -0.07
    意味
    -0.07
     nouvelle
    -0.07
    _locator
    -0.06
    POSITIVE LOGITS
    	placeholder
    0.07
    -refresh
    0.07
     throughput
    0.06
     hash
    0.06
     Valid
    0.06
     donations
    0.06
     adds
    0.06
    𝘙
    0.06
    (attribute
    0.06
    (trace
    0.06
    Activations Density 0.010%

    No Known Activations