© 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. 39645
    Prev
    Next
    INDEX
    Explanations

    roles and functions

    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
    strup
    -0.10
    adro
    -0.09
    浩
    -0.08
     espos
    -0.08
    çłº
    -0.08
    è®®é¢ĺ
    -0.08
    çģµéŃĤ
    -0.08
    orda
    -0.08
     Shortcut
    -0.08
    -bs
    -0.08
    POSITIVE LOGITS
    çļĦéĩįè¦ģæĢ§
    0.12
    çļĦä½ľçĶ¨
    0.12
    éĩįè¦ģä½ľçĶ¨
    0.11
    è´Łè´£
    0.11
    ä½ľçĶ¨
    0.11
    ä¸ĢæĹı
    0.10
    play
    0.10
     involvement
    0.10
     importance
    0.10
     important
    0.09
    Activations Density 0.973%

    No Known Activations