© 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. 49139
    Prev
    Next
    INDEX
    Explanations

    more, greater, higher

    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
    /on
    -0.10
    å·²äºİ
    -0.09
    çĥ¨
    -0.09
     sẵ
    -0.09
    åįĵ
    -0.09
    izards
    -0.09
    .Permission
    -0.09
    ahl
    -0.09
    åı²
    -0.08
    à¤Ľ
    -0.08
    POSITIVE LOGITS
    æİĮ声
    0.09
    认è¯ĨåĪ°
    0.09
    çł´ç¢İ
    0.09
    è¶Ĭ好
    0.09
    导游
    0.08
    atur
    0.08
    éĴī
    0.08
    æĪijåıijçİ°
    0.08
    åĩłçĤ¹
    0.08
    è¿Ľåĩº
    0.08
    Activations Density 0.154%

    No Known Activations