© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21986
    Prev
    Next
    INDEX
    Explanations

    he/she said/says

    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
    notated
    -0.09
    åĪ°æĿ¥
    -0.09
    éĤ£ä¹Īç®Ģåįķ
    -0.09
     *)__
    -0.09
    æѤå¤ĸ
    -0.08
    å¹³æŶ
    -0.08
    æĥħæĦŁ
    -0.08
    èĻ½çĦ¶æĺ¯
    -0.08
    åħ·ä½ĵçļĦ
    -0.08
    è¸ıä¸Ĭ
    -0.08
    POSITIVE LOGITS
    è§Ĭ
    0.10
    Invoker
    0.09
    ior
    0.09
    åı¬
    0.08
     ble
    0.08
     bree
    0.08
    沧
    0.08
    rido
    0.08
    ble
    0.08
    注æĺİæĿ¥æºIJ
    0.08
    Activations Density 0.018%

    No Known Activations