© 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. 129831
    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
    雕塑
    -0.08
    (cursor
    -0.07
    交互
    -0.07
    율
    -0.07
    -held
    -0.06
    -export
    -0.06
    BUILD
    -0.06
     quietly
    -0.06
    鉴
    -0.06
    末端
    -0.06
    POSITIVE LOGITS
    _j
    0.07
    犁
    0.07
     dataframe
    0.07
    pdo
    0.07
    קב
    0.07
    لاحق
    0.07
    时段
    0.07
    Ḵ
    0.07
     bloque
    0.07
    /orders
    0.07
    Activations Density 0.012%

    No Known Activations