© 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. 8671
    Prev
    Next
    INDEX
    Explanations

    Billboard chart numbers

    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
    以為
    -0.08
    以为
    -0.07
    阖
    -0.07
    forEach
    -0.07
     States
    -0.07
    outine
    -0.07
    咱
    -0.07
    rus
    -0.07
    蜜蜂
    -0.07
    تاب
    -0.07
    POSITIVE LOGITS
    (Product
    0.07
     Malay
    0.07
    -\
    0.07
    EndDate
    0.07
     Deluxe
    0.06
    季后
    0.06
     Multi
    0.06
    稳定性
    0.06
    سلوك
    0.06
    _mount
    0.06
    Activations Density 0.018%

    No Known Activations