© 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. 55470
    Prev
    Next
    INDEX
    Explanations

    who knows what

    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
    è¿İ
    -0.10
    å°ģ
    -0.10
    neau
    -0.09
    æħ¢æħ¢
    -0.09
    ä¹Łç®Ĺ
    -0.09
    第ä¸Ģç«ł
    -0.09
    æµ®
    -0.09
    æĵĢ
    -0.09
    çĬ¶åħĥ
    -0.09
    _VOID
    -0.09
    POSITIVE LOGITS
    ä¸įçŁ¥éģĵ
    0.13
    ä¹Łä¸įçŁ¥éģĵ
    0.13
    éĥ½ä¸įçŁ¥éģĵ
    0.11
    ä¸įçŁ¥
    0.10
    andin
    0.09
    fts
    0.09
     Miscellaneous
    0.09
    æľªçŁ¥
    0.09
    åı¯çŁ¥
    0.09
    èĥ½è¾¾åĪ°
    0.08
    Activations Density 0.037%

    No Known Activations