© 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. 23444
    Prev
    Next
    INDEX
    Explanations

    health risks, exposure

    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
    踒
    -0.07
    耏
    -0.06
     miracles
    -0.06
    ]},↵
    -0.06
    在这
    -0.06
    也有一些
    -0.06
    ilinear
    -0.06
     Rehab
    -0.06
     Arbor
    -0.06
     dominated
    -0.06
    POSITIVE LOGITS
     Moderator
    0.08
     recruiter
    0.08
    秘书
    0.07
    (gl
    0.07
     cellphone
    0.07
    (U
    0.07
    ывается
    0.07
    -connected
    0.07
    ophile
    0.07
     设
    0.07
    Activations Density 0.086%

    No Known Activations