© 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. 33415
    Prev
    Next
    INDEX
    Explanations

    it is

    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
    /her
    -0.10
    -même
    -0.10
    åħ§éĥ¨
    -0.09
    arker
    -0.09
    SELF
    -0.08
    ìĭ¶
    -0.08
     own
    -0.08
    zelf
    -0.08
    åĵº
    -0.08
    ethe
    -0.08
    POSITIVE LOGITS
    æĪijçľĭ
    0.10
    äºİæĺ¯æĪij
    0.09
    æĪijæĥ³
    0.09
    Occurred
    0.09
    æĪijå¾Ī
    0.08
    æĪijçŁ¥éģĵ
    0.08
    è¿Ļæĺ¯æĪij
    0.08
    ãģ¨ãģª
    0.08
    æĪijè§īå¾Ĺ
    0.08
    SPAN
    0.08
    Activations Density 0.196%

    No Known Activations