© 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. 4658
    Prev
    Next
    INDEX
    Explanations

    improve or gain a quality

    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
    æľºéģĩ
    -0.09
    _SECURITY
    -0.09
    RAW
    -0.09
    æijĬ
    -0.09
    æł¼å±Ģ
    -0.09
    onica
    -0.08
    indic
    -0.08
    空çĻ½
    -0.08
     warrant
    -0.08
    eyer
    -0.08
    POSITIVE LOGITS
    æ°
    0.10
    çĹ´
    0.09
    kov
    0.09
    å¤įåIJĪ
    0.09
     Klopp
    0.09
    æĩĤäºĭ
    0.09
    ä¸įæŃ»
    0.09
    alie
    0.09
    itore
    0.08
    Dispose
    0.08
    Activations Density 0.014%

    No Known Activations