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. 61892
    Prev
    Next
    INDEX
    Explanations

    from

    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
    langs
    -0.07
     eclectic
    -0.07
    <Select
    -0.07
    .lin
    -0.07
    ㋥
    -0.07
    𝙟
    -0.07
    去年
    -0.07
    DROP
    -0.06
     Kod
    -0.06
    \Contracts
    -0.06
    POSITIVE LOGITS
     terrorists
    0.07
    astered
    0.07
    所谓的
    0.07
     내가
    0.07
     Builders
    0.07
    뀌
    0.07
     nhạc
    0.07
    的问题
    0.07
    UIKit
    0.07
     thriller
    0.07
    Activations Density 0.079%

    No Known Activations