© 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. 23063
    Prev
    Next
    INDEX
    Explanations

    without

    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
    åģ¶å°Ķ
    -0.10
    ä¸įæĸŃæıIJé«ĺ
    -0.10
    åį´è¢«
    -0.10
    åıĪ好
    -0.09
    åĿĩæľī
    -0.09
     Ble
    -0.09
    çĵ¶åŃIJ
    -0.09
    æĥľ
    -0.09
    ä¸įæĸŃæıIJåįĩ
    -0.08
    ä¸įæĺĵ
    -0.08
    POSITIVE LOGITS
    没äºĨ
    0.17
    失åİ»äºĨ
    0.15
    é¡¿æŶ
    0.13
    就没æľī
    0.12
    失åİ»
    0.12
    ç«ĭåĪ»
    0.10
    å°ijäºĨ
    0.10
    ä¸įåĨį
    0.10
     ìĹĨ
    0.10
    ç«ĭåį³
    0.10
    Activations Density 0.165%

    No Known Activations