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. 131022
    Prev
    Next
    INDEX
    Explanations

    meg

    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
    ibs
    -0.07
    hits
    -0.07
     IDisposable
    -0.07
    sgi
    -0.07
     Gins
    -0.07
    星际
    -0.07
    Paths
    -0.07
    asca
    -0.07
    _static
    -0.07
    fld
    -0.07
    POSITIVE LOGITS
     בבוקר
    0.07
    Pr
    0.07
     لبن
    0.06
     Trần
    0.06
    ঔ
    0.06
     القانون
    0.06
    ضبط
    0.06
    뱅
    0.06
    ⇑
    0.06
    ubern
    0.06
    Activations Density 0.001%

    No Known Activations