© 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. 33493
    Prev
    Next
    INDEX
    Explanations

    Brotherhood or orders of

    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
    ä¹Łåıªæľī
    -0.09
    _CT
    -0.09
    ä¸ĸ家
    -0.09
    Wake
    -0.09
    åģľæĶ¾
    -0.09
     команд
    -0.09
    nap
    -0.09
    身份
    -0.09
    磬
    -0.09
    æĶ¶è´¹æłĩåĩĨ
    -0.09
    POSITIVE LOGITS
    æĹ¨åľ¨
    0.09
    æ´ģåĩĢ
    0.08
    çĺĺ
    0.08
    缩å°ı
    0.08
    _clean
    0.08
     Bow
    0.08
     Nederland
    0.08
     clean
    0.07
    认åı¯
    0.07
    çģ¶
    0.07
    Activations Density 0.036%

    No Known Activations