© 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. 57631
    Prev
    Next
    INDEX
    Explanations

    round numbers

    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
    hev
    -0.09
    ownik
    -0.09
    æ§ģ
    -0.09
    견
    -0.09
    åħĪæĺ¯
    -0.09
    opro
    -0.08
    kı
    -0.08
    VEN
    -0.08
     Wend
    -0.08
    꺼
    -0.08
    POSITIVE LOGITS
    以æѤ
    0.09
    igy
    0.09
    udu
    0.08
    躯
    0.08
    æį®æѤ
    0.08
    该项
    0.08
    éĿ¢åŃĶ
    0.08
    衽
    0.08
    adas
    0.08
    pp
    0.08
    Activations Density 0.052%

    No Known Activations