© 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. 110114
    Prev
    Next
    INDEX
    Explanations

    chemical reactions

    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
    南宋
    -0.08
     cedar
    -0.07
    谅
    -0.07
     mul
    -0.07
    ending
    -0.07
    ｘ
    -0.06
    广大
    -0.06
     mz
    -0.06
    送上
    -0.06
    李
    -0.06
    POSITIVE LOGITS
     FOUND
    0.08
    "go
    0.07
    OE
    0.07
    (sc
    0.07
    ##
    0.07
    📙
    0.07
     jours
    0.07
    oren
    0.07
    淏
    0.07
    朏
    0.07
    Activations Density 0.094%

    No Known Activations