© 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. 48217
    Prev
    Next
    INDEX
    Explanations

    to together

    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
    ãģĨãģ¡ãģ«
    -0.10
    对å¤ĸå¼ĢæĶ¾
    -0.10
    lassen
    -0.09
    cia
    -0.09
    pres
    -0.09
    OUS
    -0.09
    uci
    -0.09
    สà¸Ńà¸Ļ
    -0.09
    ãģĵãģ¨ãĤĴ
    -0.09
    æĥ¶
    -0.08
    POSITIVE LOGITS
    åīįæīĢ
    0.12
    zier
    0.11
    gether
    0.11
    GGLE
    0.10
    çĪ¶äº²
    0.10
    缮åīį为æŃ¢
    0.10
    åħ¶ä»ĸåĽ½å®¶
    0.09
    xygen
    0.09
    xic
    0.09
    æį¢äºĨ
    0.09
    Activations Density 0.095%

    No Known Activations