© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7111
    Prev
    Next
    INDEX
    Explanations

    first time / years

    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
    æ±Ĭ
    -0.10
    çĶ²éĨĽ
    -0.10
    æĪijåİ»
    -0.09
    æĺ¥è¿IJ
    -0.09
    <![
    -0.09
    æĺ¥èĬĤæľŁéĹ´
    -0.09
    使æĪij
    -0.08
    çļij
    -0.08
    æĪijèĩªå·±
    -0.08
    acia
    -0.08
    POSITIVE LOGITS
    InThe
    0.09
    çľĭçĤ¹
    0.08
    临
    0.08
    çĻ»åľº
    0.08
    odb
    0.08
    踵
    0.08
    踩
    0.08
    æij¸
    0.08
    _VARS
    0.08
     Charl
    0.08
    Activations Density 0.028%

    No Known Activations