© 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. 2287
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    æŁ¥çľĭæĽ´å¤ļ
    -0.11
    æĪijçŁ¥éģĵ
    -0.11
    ille
    -0.10
    表æĥħ
    -0.10
    æĪijä¼ļ
    -0.09
    å¤ļå¹´
    -0.09
    æĪijå¾Ī
    -0.09
    /inet
    -0.09
    åĵī
    -0.09
    ıģ
    -0.09
    POSITIVE LOGITS
     how
    0.12
    å¦Ĥä½ķ
    0.09
    ä»Ģä¹Īåı«
    0.09
    å¦Ĥä½ķåİ»
    0.08
    é¾ĥ
    0.08
    how
    0.08
    istic
    0.08
     cómo
    0.08
    åħ¶å®ŀ
    0.08
    åħ¶å¯¦
    0.08
    Activations Density 0.212%

    No Known Activations