© 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. 45064
    Prev
    Next
    INDEX
    Explanations

    summary

    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
     למצוא
    -0.08
     Invasion
    -0.07
     Fav
    -0.07
    耕
    -0.07
     spotting
    -0.07
    一世
    -0.06
    是我的
    -0.06
    .getCurrent
    -0.06
     Germ
    -0.06
    Yu
    -0.06
    POSITIVE LOGITS
    ˄
    0.07
    lä
    0.07
    lö
    0.07
    lations
    0.07
     apartheid
    0.07
    ivamente
    0.07
     ważne
    0.07
    看著
    0.07
    嚆
    0.06
    죗
    0.06
    Activations Density 0.002%

    No Known Activations