© 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. 58895
    Prev
    Next
    INDEX
    Explanations

    organizational units

    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
    éħįå¥Ĺ
    -0.11
    笥
    -0.10
    /open
    -0.10
    IFF
    -0.09
    æ³½
    -0.09
    è¡ĮæĶ¿æľºåħ³
    -0.09
    nivers
    -0.09
    å·¥åķĨèģĶ
    -0.08
    .open
    -0.08
    Sing
    -0.08
    POSITIVE LOGITS
    ç»ĪçĶŁ
    0.11
    nic
    0.10
    书é¦Ļ
    0.09
    ç»Ī身
    0.09
    åħ¶ä¸Ńä¸Ģ个
    0.09
    æĻ®åıĬ
    0.09
    ä¸Ńå¿ĥ
    0.08
    æµĵåİļ
    0.08
    ç»ĦåĽ¾
    0.08
    æĹłæīĢ
    0.08
    Activations Density 0.099%

    No Known Activations