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. 15-RESID-POST-AA
    6. 77567
    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_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
     Pipes
    -0.07
     lakh
    -0.07
    前台
    -0.06
     BET
    -0.06
     Goth
    -0.06
    鋼
    -0.06
    asher
    -0.06
     Sax
    -0.06
     chants
    -0.06
    pause
    -0.06
    POSITIVE LOGITS
     religion
    0.08
     الدنيا
    0.07
    _RW
    0.07
    .pyplot
    0.07
    �니다
    0.07
    ונו
    0.07
     wohl
    0.07
    arDown
    0.07
    właściw
    0.07
    だろう
    0.07
    Activations Density 0.003%

    No Known Activations