© 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. 19415
    Prev
    Next
    INDEX
    Explanations

    larvae feed on grasses

    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
    æģIJ
    -0.09
    æ¸Ĭ
    -0.09
    ä¸į让
    -0.09
    ELY
    -0.09
    ĺ
    -0.09
    одеÑĢж
    -0.09
    XHR
    -0.08
    nl
    -0.08
    åŁĴ
    -0.08
    lean
    -0.08
    POSITIVE LOGITS
    .biz
    0.10
    SEN
    0.10
    æŃ·
    0.09
    à¸ļà¸Ĺ
    0.09
    ibus
    0.09
    èłĭ
    0.09
    æ¡ij
    0.09
    èĻ«
    0.08
    åĴ¬
    0.08
    ivot
    0.08
    Activations Density 0.040%

    No Known Activations