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. 131060
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific context

    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
    ale
    -0.07
     Gale
    -0.07
     thrilled
    -0.07
    agt
    -0.07
    killer
    -0.07
    isl
    -0.06
    lord
    -0.06
     Blast
    -0.06
    LLL
    -0.06
    ultural
    -0.06
    POSITIVE LOGITS
    気づ
    0.08
    Ց
    0.07
     converged
    0.07
     inclus
    0.07
    egr
    0.07
     attribution
    0.07
    .waitKey
    0.07
    商用
    0.06
    ը
    0.06
    Episode
    0.06
    Activations Density 1.209%

    No Known Activations