© 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. 48482
    Prev
    Next
    INDEX
    Explanations

    `coverage` or `uptake`

    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
    泯
    -0.09
    èĩªæľī
    -0.09
    åIJij举
    -0.09
    æİ£
    -0.08
    xEC
    -0.08
    ãĦĴ
    -0.08
    åĨħåĪĨæ³Į
    -0.08
    .ids
    -0.08
    å«¡
    -0.08
    ucha
    -0.08
    POSITIVE LOGITS
    è¦ĨçĽĸçİĩ
    0.21
    åĪ©çĶ¨çİĩ
    0.16
    æĻ®åıĬ
    0.15
    çİĩ
    0.14
    è¦ĨçĽĸéĿ¢
    0.14
    çİĩè¾¾åĪ°
    0.13
    å¹¿æ³Ľ
    0.13
     coverage
    0.12
    çİĩè¾¾
    0.12
    èĩªæĦ¿
    0.12
    Activations Density 0.419%

    No Known Activations