© 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. 18053
    Prev
    Next
    INDEX
    Explanations

    sports player 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
    بر
    -0.10
    æĤĮ
    -0.09
    æIJ¦
    -0.09
    æij¸
    -0.09
    ç¢İ
    -0.09
    磮
    -0.08
    elor
    -0.08
    梯
    -0.08
    ardi
    -0.08
    å¯Ĵ
    -0.08
    POSITIVE LOGITS
    lander
    0.11
    å¥Ħ
    0.10
    æ¼Ĥ
    0.10
    è°£
    0.09
    å¤©çľŁ
    0.09
    æĿ¡çº¦
    0.09
    åĮħ袱
    0.09
    使çĶ¨èĢħæĪĸ
    0.09
     abi
    0.08
    awai
    0.08
    Activations Density 0.036%

    No Known Activations