© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 22612
    Prev
    Next
    INDEX
    Explanations

    stream

    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
     Bakery
    -0.07
    🐽
    -0.07
    쐬
    -0.07
    社会主义
    -0.07
     alternatively
    -0.07
     Vor
    -0.07
    Winvalid
    -0.07
    _ISR
    -0.07
    xor
    -0.07
     wars
    -0.07
    POSITIVE LOGITS
    칭
    0.07
    恩
    0.07
    شرف
    0.07
     Mills
    0.07
    泉
    0.07
    ồn
    0.07
    �
    0.06
    IntPtr
    0.06
     grâce
    0.06
    -known
    0.06
    Activations Density 0.002%

    No Known Activations