© 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. 42732
    Prev
    Next
    INDEX
    Explanations

    Negative situations

    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
    了些
    -0.07
    ------------------------------
    -0.07
    .nc
    -0.06
    /version
    -0.06
    ipel
    -0.06
    .lo
    -0.06
    彼此
    -0.06
    actic
    -0.06
    viar
    -0.06
     misunderstand
    -0.06
    POSITIVE LOGITS
    跪
    0.08
     sheer
    0.07
     iron
    0.07
    揭开
    0.07
     doğal
    0.07
    子孙
    0.06
    镬
    0.06
    .Factory
    0.06
     евро
    0.06
     própria
    0.06
    Activations Density 0.017%

    No Known Activations