© 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. 2100
    Prev
    Next
    INDEX
    Explanations

    love of ideas

    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
    clare
    -0.09
    aira
    -0.08
    æݧ
    -0.08
     Kend
    -0.08
    spirit
    -0.08
     Carp
    -0.08
    ushed
    -0.08
    анÑģ
    -0.08
    Caller
    -0.08
    æ±Ĺæ°´
    -0.08
    POSITIVE LOGITS
    è¶³å¤ŁçļĦ
    0.11
    çī¢åĽº
    0.11
    ä¸Ģé¢Ĺ
    0.11
    æ¬²æľĽ
    0.11
    éļ¾å¿ĺ
    0.10
    çĪ±åIJĥ
    0.10
    ä¿¡å¿ĥ
    0.09
    强çĥĪçļĦ
    0.09
    责任æĦŁ
    0.09
    osaic
    0.09
    Activations Density 0.038%

    No Known Activations