© 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. 53574
    Prev
    Next
    INDEX
    Explanations

    voice, vocal, vibration, airflow

    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
    èĻ«
    -0.11
    宣åijĬ
    -0.10
    å±¥
    -0.10
    ableView
    -0.10
    麻
    -0.09
    ä½ĵè´´
    -0.09
    æłª
    -0.09
    å¹³æĿ¿
    -0.09
    æĬĵ
    -0.09
    éĴĪ
    -0.08
    POSITIVE LOGITS
    åıij声
    0.14
    åıijéŁ³
    0.12
    åĸī
    0.12
     throat
    0.10
    éģĹ
    0.10
    åħ³éĹŃ
    0.09
    irt
    0.09
    æ¯ģ
    0.09
    åĬ¨çĶŁæĪIJ
    0.09
    åĸĿäºĨ
    0.09
    Activations Density 0.154%

    No Known Activations