© 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. 31089
    Prev
    Next
    INDEX
    Explanations

    tomato and its derivatives

    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
     Merlin
    -0.08
     getContext
    -0.08
    åħįè´£
    -0.08
    3
    -0.08
     Bid
    -0.08
     walk
    -0.08
    è´¤
    -0.08
     metals
    -0.08
    æĸ°åħ´
    -0.08
    à¹Ģà¸Ńà¸ģ
    -0.08
    POSITIVE LOGITS
    è¥¿çº¢æŁ¿
    0.14
    çķªèĮĦ
    0.13
    èĮĦåŃIJ
    0.13
     Tomato
    0.12
    ðŁįħ
    0.12
     tomato
    0.11
     tomatoes
    0.11
    é¢Ķ
    0.10
    çģ¯ç¬¼
    0.10
    大桥
    0.10
    Activations Density 0.044%

    No Known Activations