© 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. 53820
    Prev
    Next
    INDEX
    Explanations

    yet to

    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
    è£ķ
    -0.10
    stuff
    -0.10
    åĽŀæĥ³
    -0.09
    å®ĮäºĨ
    -0.09
    avin
    -0.09
    马ä¸Ĭå°±
    -0.08
    åĨ³ä¸į
    -0.08
    åıªè¦ģæľī
    -0.08
    æĭ¿æĿ¥
    -0.08
    æ»ħ
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.11
    ertiary
    0.10
    acity
    0.10
    æıIJåıĬ
    0.09
    ened
    0.09
     cá»Ń
    0.09
    ucht
    0.09
    rous
    0.09
    /current
    0.08
    å®ŀè´¨æĢ§
    0.08
    Activations Density 0.007%

    No Known Activations