© 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. 61431
    Prev
    Next
    INDEX
    Explanations

    chiral and related notation

    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
    å¾Ĺ好
    -0.08
    etas
    -0.08
    æ²Ł
    -0.08
    çĤķ
    -0.08
    èģĶ
    -0.08
     Nich
    -0.08
    转载请
    -0.08
     kne
    -0.08
    Nich
    -0.08
    _Header
    -0.08
    POSITIVE LOGITS
    åıĮåıĮ
    0.11
    æµĬ
    0.11
    inkel
    0.09
     pall
    0.09
    èį¡
    0.09
    éı¡
    0.09
    æ¸ħæ¾Ī
    0.09
     Trouble
    0.09
    çģ¯åħī
    0.09
    assy
    0.09
    Activations Density 0.060%

    No Known Activations