© 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. 979
    Prev
    Next
    INDEX
    Explanations

    mushroom and fungi

    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
     impro
    -0.09
    OrNil
    -0.09
    å®īéĿĻ
    -0.08
    翻身
    -0.08
    åĬ¨åĬĽ
    -0.08
    iou
    -0.08
    çĴĭ
    -0.08
    Scoped
    -0.08
    æ³±
    -0.08
    ople
    -0.08
    POSITIVE LOGITS
    èĺijèıĩ
    0.18
    èıĩ
    0.16
     mushrooms
    0.15
    ðŁįĦ
    0.15
    èıĮ
    0.14
    æľ¨èĢ³
    0.13
     Mushroom
    0.12
     mushroom
    0.12
    èķĪ
    0.12
     Mush
    0.11
    Activations Density 0.052%

    No Known Activations