© 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. 5450
    Prev
    Next
    INDEX
    Explanations

    then

    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
    밥
    -0.07
     Oct
    -0.07
    .btnCancel
    -0.07
     herself
    -0.07
    opping
    -0.06
    拥护
    -0.06
    翅膀
    -0.06
     tantal
    -0.06
     przec
    -0.06
    jun
    -0.06
    POSITIVE LOGITS
    معال
    0.09
     danh
    0.08
     Gh
    0.07
    <Action
    0.07
     Timeout
    0.07
    _gui
    0.07
     Left
    0.07
    光源
    0.07
    -switch
    0.07
    ⧽
    0.07
    Activations Density 0.007%

    No Known Activations