© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9049
    Prev
    Next
    INDEX
    Explanations

    plumped, popped, unk, ack, uck

    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
    è¢į
    -0.10
    è½»è½»åľ°
    -0.09
     lược
    -0.09
     Ellison
    -0.09
    ç§ijæĻ®
    -0.09
     Тем
    -0.09
    iddles
    -0.08
    æĪĺ士
    -0.08
    compass
    -0.08
     Bair
    -0.08
    POSITIVE LOGITS
    uate
    0.10
    ter
    0.10
    æĹĦ
    0.10
    ä¸Ĭåİ»
    0.08
    åľī
    0.08
    ãĥ§ãĥ³
    0.08
    åĩĨç¡®æĢ§
    0.08
    /pi
    0.08
    åijĨ
    0.08
    astic
    0.08
    Activations Density 0.011%

    No Known Activations