© 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. 129781
    Prev
    Next
    INDEX
    Explanations

    quantum physics

    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
    朴实
    -0.08
    က
    -0.07
     prise
    -0.07
    禧
    -0.07
    点点头
    -0.07
    uali
    -0.07
    ocode
    -0.07
    挈
    -0.07
     wisdom
    -0.07
    _FLAG
    -0.07
    POSITIVE LOGITS
     Перв
    0.07
     relations
    0.07
    דעות
    0.07
     Ch
    0.07
     tracked
    0.06
     É
    0.06
    曲
    0.06
     bụ
    0.06
     Singular
    0.06
    Also
    0.06
    Activations Density 0.017%

    No Known Activations