© 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. 89635
    Prev
    Next
    INDEX
    Explanations

    wizard

    np_max-act · gemini-2.0-flash

    references to software “wizard” interfaces or components, especially in code or UI contexts

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     CC
    -0.08
    AŞ
    -0.07
    CC
    -0.07
    됨
    -0.07
    "><?=
    -0.07
    .getAs
    -0.06
     являются
    -0.06
    Fuse
    -0.06
     appe
    -0.06
    tere
    -0.06
    POSITIVE LOGITS
    .UI
    0.08
     wizards
    0.08
    뎐
    0.07
    𝘄
    0.07
    掌
    0.07
    绉
    0.07
    澽
    0.07
     הרב
    0.07
    幌
    0.07
    陟
    0.07
    Activations Density 0.006%

    No Known Activations