© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22321
    Prev
    Next
    INDEX
    Explanations

    providing or updating websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .bulk
    -0.09
    _SPE
    -0.09
    chas
    -0.09
    ë³ij
    -0.09
    JsonProperty
    -0.09
     Whatsapp
    -0.09
    еÑģÑĤво
    -0.09
    ugh
    -0.09
    è¿ĻäºĽéĹ®é¢ĺ
    -0.09
    èħ®
    -0.09
    POSITIVE LOGITS
     site
    0.17
    ç½ijç«Ļ
    0.16
    åŁŁåIJį
    0.14
    site
    0.13
    æµģéĩı
    0.13
     sites
    0.13
    (site
    0.13
    ç«ĻçĤ¹
    0.13
    SITE
    0.12
    页éĿ¢
    0.12
    Activations Density 0.159%

    No Known Activations