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. 130986
    Prev
    Next
    INDEX
    Explanations

    comic books

    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
    main
    -0.07
    orneys
    -0.06
    亩
    -0.06
    rowave
    -0.06
     кл
    -0.06
     individuals
    -0.06
    	Vec
    -0.06
    通关
    -0.06
    iping
    -0.06
    Het
    -0.06
    POSITIVE LOGITS
    oufl
    0.07
    内马
    0.07
    的根本
    0.07
     disgu
    0.07
    ención
    0.07
    至尊
    0.06
    angepicker
    0.06
    DOB
    0.06
    cff
    0.06
    platz
    0.06
    Activations Density 0.030%

    No Known Activations