© 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. 36128
    Prev
    Next
    INDEX
    Explanations

    cyrillic letters

    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
    å°±èĥ½å¤Ł
    -0.10
    lık
    -0.09
    noon
    -0.09
    æĺ¯æĪijçļĦ
    -0.09
    s
    -0.09
    nya
    -0.08
    ãģªãģĭ
    -0.08
    nel
    -0.08
    haft
    -0.08
     Presents
    -0.08
    POSITIVE LOGITS
    поÑĤ
    0.11
    бо
    0.11
    amp
    0.11
    ey
    0.10
    å·¥ä½ľæĸ¹æ¡Ī
    0.10
    ä»İä¸Ń
    0.10
    å®ŀéĻħè¡ĮåĬ¨
    0.10
    olk
    0.10
    /or
    0.10
    ceeded
    0.09
    Activations Density 0.022%

    No Known Activations