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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23-RESID-POST-AA
    11. 129858
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MING
    -0.07
     diary
    -0.07
     FREE
    -0.06
    高原
    -0.06
     jackets
    -0.06
     unn
    -0.06
     RAID
    -0.06
     Falcons
    -0.06
     dopo
    -0.06
    ıyor
    -0.06
    POSITIVE LOGITS
    活力
    0.07
    み
    0.07
    服务能力
    0.07
    �
    0.07
    ;base
    0.07
    ведите
    0.06
     Instruments
    0.06
     Chr
    0.06
    /gr
    0.06
     "}↵
    0.06
    Activations Density 0.002%

    No Known Activations