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. 19-RESID-POST-AA
    6. 130509
    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -series
    -0.07
    .getRuntime
    -0.07
    提供优质
    -0.07
    ปร
    -0.06
    马来西亚
    -0.06
    currentState
    -0.06
     PRI
    -0.06
    GetString
    -0.06
     giữa
    -0.06
    arti
    -0.06
    POSITIVE LOGITS
     coating
    0.07
     *</
    0.07
    ↛
    0.06
     paragraphs
    0.06
     linewidth
    0.06
     conex
    0.06
     exon
    0.06
    another
    0.06
    澶
    0.06
    咔
    0.06
    Activations Density 0.023%

    No Known Activations