© 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. 75050
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    杩
    -0.08
    ipmap
    -0.07
    ین
    -0.07
    <|im_start|>
    -0.07
     Illum
    -0.07
    踒
    -0.07
     OnDestroy
    -0.07
    ôt
    -0.07
    /window
    -0.07
    砹
    -0.07
    POSITIVE LOGITS
    (str
    0.07
    (Level
    0.07
    (bg
    0.07
     Vale
    0.07
     الرقم
    0.06
    (Image
    0.06
     للت
    0.06
    (tol
    0.06
    CURRENT
    0.06
    都非常
    0.06
    Activations Density 0.191%

    No Known Activations