© 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. 18519
    Prev
    Next
    INDEX
    Explanations

    tool holder, machining, materials

    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
    æ¢Ń
    -0.10
    acid
    -0.10
     اÙĦعÙħ
    -0.10
    åĭį
    -0.09
    -links
    -0.08
    lds
    -0.08
    mob
    -0.08
    åĩ¤åĩ°
    -0.08
    æĺ¶
    -0.08
    è¿ľç¦»
    -0.08
    POSITIVE LOGITS
    åħ¨å¥Ĺ
    0.09
     tÃł
    0.09
    åĩłåIJį
    0.08
    带头
    0.08
    rieve
    0.08
    æģŃ
    0.08
    steen
    0.08
     Eag
    0.08
    åĽ½éģĵ
    0.08
    è°
    0.08
    Activations Density 0.140%

    No Known Activations