© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19968
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
    obar
    -0.09
    æIJĶ
    -0.08
     Dob
    -0.08
    åĴİ
    -0.08
    骥
    -0.08
    agy
    -0.08
    emer
    -0.08
    itty
    -0.08
    æħİ
    -0.08
    ĵåIJį
    -0.08
    POSITIVE LOGITS
    æĦĪ
    0.09
    æİĴè¡Į
    0.09
    éĺ¶æ®µæĢ§
    0.09
    _pending
    0.09
    åĻ¨åħ·
    0.08
     Malone
    0.08
    åĩĿèģļåĬĽ
    0.08
    交æµģåIJĪä½ľ
    0.08
    vert
    0.08
    åħŃåIJĪ
    0.08
    Activations Density 0.342%

    No Known Activations