© 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. 77541
    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
     imped
    -0.07
    outside
    -0.07
    陛
    -0.07
    _SPECIAL
    -0.07
    ibal
    -0.06
     времени
    -0.06
    hör
    -0.06
    зв
    -0.06
    红色
    -0.06
    KC
    -0.06
    POSITIVE LOGITS
     сахар
    0.08
     touted
    0.06
     thấp
    0.06
     yield
    0.06
    ]];
    0.06
     **/↵↵
    0.06
    划分
    0.06
    .algorithm
    0.06
    始终坚持
    0.06
     Cosmetic
    0.06
    Activations Density 0.112%

    No Known Activations