© 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. 32992
    Prev
    Next
    INDEX
    Explanations

    today's relevance or current state

    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
    æİ®
    -0.10
    æĬ¼
    -0.09
    mania
    -0.09
     ÄIJo
    -0.09
    çĭĻ
    -0.09
    иков
    -0.09
    åĿıäºĭ
    -0.09
    enas
    -0.09
    ylv
    -0.09
    æĸ°å¨ĺ
    -0.09
    POSITIVE LOGITS
    为æŃ¢
    0.10
    å±ĢéĿ¢
    0.10
    itor
    0.09
    é«ĺ级
    0.08
    moth
    0.08
    helper
    0.08
    ales
    0.08
    æĥ®
    0.08
    ãĥ¬ãĤ¤
    0.08
    macros
    0.08
    Activations Density 0.026%

    No Known Activations