© 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. 23233
    Prev
    Next
    INDEX
    Explanations

    official, website, safari

    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
    ç¬ij声
    -0.09
    æ¯ĶæĪij
    -0.09
     Ph
    -0.09
    çĺª
    -0.09
    èĪľ
    -0.08
    ноп
    -0.08
    ä»Ģ麽
    -0.08
    æ¼¾
    -0.08
    null
    -0.08
    æľ¬é¢Ĩ
    -0.08
    POSITIVE LOGITS
     Pais
    0.10
    ysz
    0.10
    æĭľ
    0.09
    称åı·
    0.09
    SCO
    0.09
    çĪµ
    0.09
    åĤ»
    0.09
    åĥŃ
    0.09
    å°ģ
    0.09
    iasm
    0.09
    Activations Density 0.091%

    No Known Activations