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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19-RESID-POST-AA
    11. 8041
    Prev
    Next
    INDEX
    Explanations

    Events happening at times

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ProducesResponseType
    -0.08
    辿
    -0.07
    レス
    -0.07
    SQLException
    -0.07
    completed
    -0.07
    🔉
    -0.07
    תיאור
    -0.07
     צפו
    -0.07
    ㌦
    -0.07
    瘗
    -0.07
    POSITIVE LOGITS
     throw
    0.08
    窗户
    0.08
     HE
    0.07
    ㉯
    0.07
     Seek
    0.07
     MAG
    0.07
    supplier
    0.07
     matter
    0.07
     braz
    0.07
     Sk
    0.07
    Activations Density 0.167%

    No Known Activations