© 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. 55688
    Prev
    Next
    INDEX
    Explanations

    you may/can/must/should

    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
    åľ¨äº¬
    -0.09
    åĻ±
    -0.09
    è¿ĩåİ»çļĦ
    -0.09
    çĺ«
    -0.09
    åĸĺ
    -0.09
    chy
    -0.09
    resident
    -0.09
    elize
    -0.08
    为æĬĵæīĭ
    -0.08
    qa
    -0.08
    POSITIVE LOGITS
    ä¸įå¾Ĺ
    0.12
    è´Ł
    0.09
    åºĶ注æĦı
    0.09
    åĭ¿
    0.09
    éģµå®Ī
    0.09
    çķĻæĦı
    0.09
    è¦ģ注æĦı
    0.09
    ä¸įèµ·
    0.09
    ohl
    0.09
    è°¨
    0.08
    Activations Density 0.036%

    No Known Activations