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. 131010
    Prev
    Next
    INDEX
    Explanations

    say ":"

    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
    ellas
    -0.07
    isoner
    -0.07
     Publishing
    -0.07
    leaning
    -0.07
    אב
    -0.06
    allenge
    -0.06
     vigilant
    -0.06
     оста
    -0.06
    CTIONS
    -0.06
    omit
    -0.06
    POSITIVE LOGITS
     data
    0.07
    -inverse
    0.07
    trade
    0.07
     tst
    0.07
    .PrintWriter
    0.07
    rug
    0.07
     Neuro
    0.06
     dise
    0.06
    羲
    0.06
    (deg
    0.06
    Activations Density 0.025%

    No Known Activations