© 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. 77155
    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
     самостоятельно
    -0.08
    模仿
    -0.08
    /context
    -0.07
     accordingly
    -0.07
    ᴹ
    -0.07
    =
    -0.07
     imprison
    -0.07
     individually
    -0.07
     clothing
    -0.07
     adjusted
    -0.07
    POSITIVE LOGITS
    泓
    0.07
    ȍ
    0.07
    État
    0.07
     Elig
    0.07
    ænd
    0.06
    بيعي
    0.06
    rvine
    0.06
    🏞
    0.06
     dign
    0.06
    忑
    0.06
    Activations Density 0.022%

    No Known Activations