© 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. 9755
    Prev
    Next
    INDEX
    Explanations

    racetrack, raccoons, racism, racemic

    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
    ÐĿÐķ
    -0.08
    äºĨåĩºæĿ¥
    -0.08
    ä¸İåıijå±ķ
    -0.08
    éĤĪ
    -0.08
    orary
    -0.08
    åıªä¸įè¿ĩ
    -0.08
    spots
    -0.08
    æĻ¡
    -0.08
    edly
    -0.08
    uard
    -0.08
    POSITIVE LOGITS
    ellas
    0.11
    iffs
    0.11
    åĥ®
    0.11
    ãĥ¬ãĤ¹
    0.10
    erea
    0.10
    沤
    0.09
    tails
    0.09
    สà¸Ļ
    0.09
    tail
    0.09
    尾巴
    0.09
    Activations Density 0.003%

    No Known Activations