© 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. 48846
    Prev
    Next
    INDEX
    Explanations

    system failures and errors

    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
    Iso
    -0.07
     feeder
    -0.07
     đường
    -0.07
     expansions
    -0.06
     Bank
    -0.06
    負責
    -0.06
     Computes
    -0.06
     tiểu
    -0.06
     expansion
    -0.06
     план
    -0.06
    POSITIVE LOGITS
    MOTE
    0.08
    (dllexport
    0.07
    .dylib
    0.07
    電子郵件
    0.07
    ULATE
    0.07
    ATORY
    0.07
    ERNEL
    0.07
     ---↵
    0.07
    .returnValue
    0.06
    ˓
    0.06
    Activations Density 0.088%

    No Known Activations