© 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. 8961
    Prev
    Next
    INDEX
    Explanations

    experience possible

    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
    é©Ń
    -0.09
    æ¡£
    -0.09
    åħ¨åĽ½äººæ°ij
    -0.08
    æĥħæĬ¥
    -0.08
    åIJ¬äºĨ
    -0.08
    æĦŁè§¦
    -0.08
    ç¦Ĭ
    -0.08
     Riv
    -0.08
    ife
    -0.08
    rive
    -0.08
    POSITIVE LOGITS
    umph
    0.10
    åįķåįķ
    0.09
    .blob
    0.08
    åİŁåŀĭ
    0.08
    ä¾®
    0.08
     ----------------------------------------------------------------------------↵
    0.08
    estimated
    0.08
    shal
    0.08
    æ¢ħèĬ±
    0.08
    çķĻåŃĺ
    0.08
    Activations Density 0.010%

    No Known Activations