© 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. 53044
    Prev
    Next
    INDEX
    Explanations

    vegan, vegetarian, veggie, vegetation

    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
    è´¶
    -0.09
    è§ģ解
    -0.09
    osas
    -0.09
    磷
    -0.09
     Ferr
    -0.08
    ä¿Ĺ
    -0.08
    à´´
    -0.08
    è¾ķ
    -0.08
     вÑĭпÑĥÑģк
    -0.08
     Trouble
    -0.08
    POSITIVE LOGITS
    å»¶æľŁ
    0.09
    ä½ķåĨµ
    0.09
    æĩĴ
    0.09
    æµĵåİļ
    0.09
    人å±ħ
    0.08
    lund
    0.08
    etter
    0.08
    èĮ«èĮ«
    0.08
    _critical
    0.08
    hti
    0.08
    Activations Density 0.013%

    No Known Activations