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. 131026
    Prev
    Next
    INDEX
    Explanations

    XML data

    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
    phants
    -0.08
    .salary
    -0.08
    UpDown
    -0.08
    .Decode
    -0.07
     splitting
    -0.07
    ทำไม
    -0.07
     ivory
    -0.07
     почему
    -0.07
     gbc
    -0.07
    姗
    -0.07
    POSITIVE LOGITS
    恶
    0.07
    事实
    0.07
     nestled
    0.07
    ))^
    0.07
     :]
    0.06
    预计将
    0.06
    ][/
    0.06
    .DATE
    0.06
     Claude
    0.06
    士
    0.06
    Activations Density 0.056%

    No Known Activations