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. 131005
    Prev
    Next
    INDEX
    Explanations

    say where

    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
    (song
    -0.09
    甗
    -0.07
    -sex
    -0.07
    �
    -0.07
     uncomp
    -0.07
     אירוע
    -0.07
    stdexcept
    -0.07
    裨
    -0.07
    ┘
    -0.07
    sembl
    -0.07
    POSITIVE LOGITS
    📌
    0.07
    xxxxxxxx
    0.07
    助攻
    0.06
     Whitney
    0.06
    ita
    0.06
    公告
    0.06
     complete
    0.06
     Messiah
    0.06
    ittle
    0.06
     dólares
    0.06
    Activations Density 0.326%

    No Known Activations