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. 11-RESID-POST-AA
    6. 87108
    Prev
    Next
    INDEX
    Explanations

    sports team performance

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antagon
    -0.08
     Epic
    -0.07
    vid
    -0.07
     VP
    -0.07
    急
    -0.06
    /context
    -0.06
    面前
    -0.06
    .Register
    -0.06
    Subscribe
    -0.06
     skept
    -0.06
    POSITIVE LOGITS
     thác
    0.07
    (Float
    0.07
     Unt
    0.07
    蕰
    0.07
    敬畏
    0.07
     understands
    0.07
     טבע
    0.07
    .Bus
    0.07
     ageing
    0.06
     protobuf
    0.06
    Activations Density 0.026%

    No Known Activations