© 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. 15-RESID-POST-AA
    11. 85285
    Prev
    Next
    INDEX
    Explanations

    recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ữ
    -0.07
     Lexus
    -0.07
     Marl
    -0.07
    odia
    -0.06
    angu
    -0.06
     character
    -0.06
    数码
    -0.06
     Intelli
    -0.06
    -unit
    -0.06
    而对于
    -0.06
    POSITIVE LOGITS
     şikayet
    0.07
    .leave
    0.07
     layers
    0.06
    喳
    0.06
    Sort
    0.06
    เ
    0.06
    죔
    0.06
     �
    0.06
     śro
    0.06
    _EVAL
    0.06
    Activations Density 0.038%

    No Known Activations