© 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. 115670
    Prev
    Next
    INDEX
    Explanations

    variable

    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
    nm
    -0.08
    ﳌ
    -0.08
    =train
    -0.07
    [b
    -0.07
    不同
    -0.07
     wrench
    -0.07
    uesta
    -0.06
    自学
    -0.06
    flash
    -0.06
    -neck
    -0.06
    POSITIVE LOGITS
     עוב
    0.07
    /↵↵
    0.07
    康熙
    0.07
     loc
    0.07
    .Controls
    0.07
    _der
    0.07
    ὓ
    0.07
     Progress
    0.06
    برا
    0.06
    郿
    0.06
    Activations Density 0.002%

    No Known Activations