© 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. 19-RESID-POST-AA
    11. 89515
    Prev
    Next
    INDEX
    Explanations

    depths

    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
    idée
    -0.08
     caratter
    -0.07
     כאן
    -0.07
    iginal
    -0.07
     ensured
    -0.07
     vier
    -0.06
    ieving
    -0.06
     Judicial
    -0.06
     mandated
    -0.06
    ady
    -0.06
    POSITIVE LOGITS
    鳖
    0.07
    ♝
    0.07
    下巴
    0.07
    \Bridge
    0.07
    [strlen
    0.06
    getNode
    0.06
    ᐈ
    0.06
     לט
    0.06
    אחד
    0.06
    /****************************************************************************
    0.06
    Activations Density 0.013%

    No Known Activations