© 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. 5604
    Prev
    Next
    INDEX
    Explanations

    then expressions

    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
    ingly
    -0.10
    tail
    -0.09
    elyn
    -0.08
    utsch
    -0.08
    tes
    -0.08
    antro
    -0.08
    	atomic
    -0.08
    ters
    -0.08
    tern
    -0.08
    ende
    -0.08
    POSITIVE LOGITS
    igma
    0.10
    åŃIJå¼Ł
    0.10
    èѬå¦Ĥ
    0.10
    主è§Ĥ
    0.09
    ä¹Łå¥½
    0.09
    æ¯Ķå¦Ĥ说
    0.09
    è¿Ļæī¹
    0.09
    åIJ¦
    0.09
    åĽ¢éķ¿
    0.09
    æĽ·
    0.09
    Activations Density 0.033%

    No Known Activations