Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 131053
    Prev
    Next
    INDEX
    Explanations

    F

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defines
    -0.07
    净
    -0.07
     Ż
    -0.07
     deductible
    -0.07
     scrolls
    -0.07
    ((*
    -0.07
     Lemma
    -0.07
    笼罩
    -0.07
     Ensure
    -0.06
    _define
    -0.06
    POSITIVE LOGITS
     AVCapture
    0.07
    횔
    0.07
     Theodore
    0.07
    喉咙
    0.07
     esposa
    0.06
    วรรณ
    0.06
     במקרים
    0.06
    愦
    0.06
     Moder
    0.06
    เศรษฐ
    0.06
    Activations Density 0.001%

    No Known Activations