© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 89383
    Prev
    Next
    INDEX
    Explanations

    üss

    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
     Ком
    -0.09
    .Pe
    -0.09
     cuc
    -0.08
    _Ph
    -0.08
    -ca
    -0.08
    _tele
    -0.08
     INS
    -0.08
    Sil
    -0.08
     Dy
    -0.08
     colony
    -0.08
    POSITIVE LOGITS
     Fail
    0.08
    売
    0.08
    .rand
    0.07
    正是因为
    0.07
    struct
    0.07
     owner
    0.07
    size
    0.07
    .assert
    0.07
    寁
    0.07
    就是因为
    0.07
    Activations Density 1.798%

    No Known Activations