© 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. 27669
    Prev
    Next
    INDEX
    Explanations

    folio or follicle

    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
    جاز
    -0.10
    ä¿IJ
    -0.10
    جاÙĦ
    -0.10
    íĴĢ
    -0.09
    çĵ¶
    -0.09
    bart
    -0.09
    ingly
    -0.09
    çļ¿
    -0.09
     mắt
    -0.09
    fully
    -0.08
    POSITIVE LOGITS
    åħ¬å¼Ģåıijè¡Į
    0.09
    ings
    0.09
    own
    0.09
    arity
    0.08
    ename
    0.08
    hape
    0.08
    igar
    0.08
    theme
    0.08
    ks
    0.08
    orgen
    0.08
    Activations Density 0.015%

    No Known Activations