© 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. 9804
    Prev
    Next
    INDEX
    Explanations

    wild animal or plant

    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
    åĸĦæĦı
    -0.09
    oled
    -0.09
    æľºç»Ħ
    -0.09
     staÅĤ
    -0.08
    æĦŁè§¦
    -0.08
    _placement
    -0.08
    oogle
    -0.08
    è¯Ī
    -0.08
    aur
    -0.08
    hip
    -0.08
    POSITIVE LOGITS
    ness
    0.11
    craft
    0.11
    æľĭåıĭ们
    0.10
    -minded
    0.08
    eren
    0.08
    代çIJĨ人
    0.08
    legen
    0.08
    locks
    0.08
    вин
    0.08
    haven
    0.08
    Activations Density 0.008%

    No Known Activations