© 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. 5346
    Prev
    Next
    INDEX
    Explanations

    Songs

    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
    𫠜
    -0.07
    xmlns
    -0.07
     UD
    -0.07
    plete
    -0.07
     Voters
    -0.07
    ariance
    -0.07
    oure
    -0.07
     категор
    -0.06
    .gf
    -0.06
    ="#"><
    -0.06
    POSITIVE LOGITS
    기도
    0.08
    )])
    0.08
    論
    0.07
    ↵↵↵↵↵
    0.07
    本质上
    0.07
     planets
    0.07
    推测
    0.07
     Lord
    0.07
    기
    0.07
    앗
    0.07
    Activations Density 0.133%

    No Known Activations