© 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. 54873
    Prev
    Next
    INDEX
    Explanations

    animal names

    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
    éĶ¦ç»£
    -0.09
    illy
    -0.09
    OrUpdate
    -0.09
    è¢ĸ
    -0.08
     '\'
    -0.08
    ä¸ĸçķĮ第ä¸Ģ
    -0.08
    uler
    -0.08
    erson
    -0.08
    éĽĩ
    -0.08
    çIJ¼
    -0.08
    POSITIVE LOGITS
    尾巴
    0.11
    èĪ¬çļĦ
    0.10
    fish
    0.10
    hood
    0.10
    ishly
    0.10
    trap
    0.10
    çĪª
    0.10
    -shaped
    0.09
    EMU
    0.09
    à¸ģระà¸Ĺ
    0.09
    Activations Density 0.278%

    No Known Activations