© 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. 15-RESID-POST-AA
    11. 77404
    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
    ournament
    -0.07
    Ctx
    -0.07
     Employment
    -0.07
     submissive
    -0.07
    kel
    -0.06
    -comment
    -0.06
    .validator
    -0.06
    ultimate
    -0.06
    _not
    -0.06
    需要用到
    -0.06
    POSITIVE LOGITS
    噪声
    0.07
     ajax
    0.07
    錄
    0.07
    直流
    0.07
     ACM
    0.07
     lasers
    0.07
    物联网
    0.07
     odd
    0.07
    浰
    0.07
    技术创新
    0.07
    Activations Density 0.004%

    No Known Activations