© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63672
    Prev
    Next
    INDEX
    Explanations

    cone or sphere shape

    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
    ness
    -0.14
    omics
    -0.11
    ocrin
    -0.10
    éĿŀåĩ¡
    -0.10
     sÃłng
    -0.09
    ãģ³
    -0.09
    иÑĢовки
    -0.09
     Reflex
    -0.09
    é«®
    -0.09
    owel
    -0.09
    POSITIVE LOGITS
    lö
    0.11
    ical
    0.11
    illing
    0.10
    -shaped
    0.09
    PIP
    0.09
    ãģ£ãģ¨
    0.09
    éĺĬ
    0.09
    åĨħçļĦ
    0.09
     деÑıÑĤелÑĮноÑģÑĤи
    0.09
    cko
    0.09
    Activations Density 0.040%

    No Known Activations