© 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. 20046
    Prev
    Next
    INDEX
    Explanations

    Fisheries, fishing, fisherman

    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
    enance
    -0.11
    æ·±å¤Ħ
    -0.09
    å±ĤéĿ¢
    -0.09
    heet
    -0.08
    ä¸ĩéĩĮ
    -0.08
    èĬ¡
    -0.08
     Grat
    -0.08
    æ±Ĺ
    -0.08
    ä¸Ģç«Ļ
    -0.08
    iper
    -0.08
    POSITIVE LOGITS
    ãĥ³ãĥī
    0.11
    æķ´é¡¿
    0.10
     Cald
    0.09
    horn
    0.09
    æѸ
    0.09
     trout
    0.09
    å½Ĵ
    0.08
    ðŁIJŁ
    0.08
    zc
    0.08
     tuna
    0.08
    Activations Density 0.024%

    No Known Activations