© 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. 6816
    Prev
    Next
    INDEX
    Explanations

    outing, endeavor, excursion

    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
    ç¾¹
    -0.09
    æį¢å±Ĭ
    -0.09
    以便
    -0.08
    çĶŁæ´»çݯå¢ĥ
    -0.08
    å¼ĢåıijèĢħ
    -0.08
    æĥ³ä¸įåĪ°
    -0.08
    æĢĢçĿĢ
    -0.08
    /null
    -0.08
    åį£
    -0.08
    OrNull
    -0.07
    POSITIVE LOGITS
    æ¯ķç«Ł
    0.10
    educt
    0.10
    æĮ«æĬĺ
    0.09
    orama
    0.09
    æ¯ķç«Łæĺ¯
    0.09
    åħīå½±
    0.09
    :expr
    0.08
    .Tick
    0.08
    足以
    0.08
    thic
    0.08
    Activations Density 0.021%

    No Known Activations