Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 288
    Prev
    Next
    INDEX
    Explanations

    software

    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_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
    GameManager
    -0.07
     coz
    -0.07
     rub
    -0.07
    輸
    -0.07
     yük
    -0.07
     tri
    -0.07
     clic
    -0.07
    Advertis
    -0.07
    妭
    -0.06
    Franc
    -0.06
    POSITIVE LOGITS
     Spaces
    0.08
    onders
    0.07
     Ways
    0.07
    בוחר
    0.07
    (delay
    0.07
    .System
    0.07
    职能
    0.06
    ഹ
    0.06
    itches
    0.06
    𬒈
    0.06
    Activations Density 0.000%

    No Known Activations