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. 56427
    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
    乎
    -0.07
    伙伴
    -0.07
     lightly
    -0.07
    有意
    -0.07
     ومع
    -0.07
    玱
    -0.07
    게
    -0.07
    涕
    -0.07
     LETTER
    -0.07
    إعداد
    -0.06
    POSITIVE LOGITS
     pelvic
    0.08
     Ibrahim
    0.07
     Dy
    0.07
    Body
    0.07
     puck
    0.07
     Apprentice
    0.07
    _width
    0.07
    itemId
    0.07
    }px
    0.07
     Rodney
    0.07
    Activations Density 0.045%

    No Known Activations