© 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. 56822
    Prev
    Next
    INDEX
    Explanations

    driving

    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
    avy
    -0.11
    åĩºåĵģ
    -0.10
    aire
    -0.10
     assignable
    -0.09
    neo
    -0.09
    è¾½
    -0.09
    æ¸ł
    -0.09
    éĩľ
    -0.09
    çļĦè¡Į为
    -0.09
    åıijå±ķ壮大
    -0.09
    POSITIVE LOGITS
    éĺIJ
    0.09
    åĪ°åºķ
    0.09
    peat
    0.08
    éļ
    0.08
    abbrev
    0.08
    é²²
    0.08
    ä¸ŀ
    0.08
    åĹIJ
    0.08
    eling
    0.08
    æį¢æĪIJ
    0.08
    Activations Density 0.029%

    No Known Activations