© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 49202
    Prev
    Next
    INDEX
    Explanations

    var

    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_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
    _lua
    -0.07
     bufio
    -0.07
    /control
    -0.07
     vign
    -0.07
     covered
    -0.07
    ответ
    -0.07
    .unwrap
    -0.07
    𝒊
    -0.07
    obl
    -0.06
    𝑽
    -0.06
    POSITIVE LOGITS
    {{--
    0.07
    Cat
    0.06
    发展阶段
    0.06
    一直都
    0.06
    物业公司
    0.06
     Often
    0.06
     köln
    0.06
    总工会
    0.06
     Dere
    0.06
    刻
    0.06
    Activations Density 0.001%

    No Known Activations