© 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. 33196
    Prev
    Next
    INDEX
    Explanations

    garlic cloves

    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
    oped
    -0.09
    æŁĶ
    -0.09
    ops
    -0.09
    åįĥåħĥ
    -0.08
     Sands
    -0.08
    Nation
    -0.08
    åľºéĿ¢
    -0.08
     pat
    -0.08
    ugg
    -0.08
    hei
    -0.08
    POSITIVE LOGITS
     cloves
    0.11
     Garlic
    0.10
    bay
    0.10
     bulbs
    0.10
     bulb
    0.09
    _NUMERIC
    0.09
    éĶĻè¿ĩ
    0.09
     clo
    0.09
    äººæł¼
    0.09
    大èĴľ
    0.09
    Activations Density 0.024%

    No Known Activations