© 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. 23-RESID-POST-AA
    11. 129876
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urations
    -0.07
    菘
    -0.07
    _character
    -0.07
     indebted
    -0.07
    킨
    -0.07
    盯
    -0.07
    (xpath
    -0.07
    bye
    -0.06
     conjug
    -0.06
    刪
    -0.06
    POSITIVE LOGITS
     acceler
    0.07
    预期
    0.07
    字号
    0.07
    erves
    0.06
    不受
    0.06
    ound
    0.06
     SUS
    0.06
    /downloads
    0.06
    CREEN
    0.06
    减弱
    0.06
    Activations Density 0.029%

    No Known Activations