© 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. 35708
    Prev
    Next
    INDEX
    Explanations

    bay followed by place names

    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
    andal
    -0.11
    天涯
    -0.10
    .ArgumentParser
    -0.10
    berger
    -0.10
    ente
    -0.09
    æĪij以为
    -0.09
    sr
    -0.09
    ENTE
    -0.09
    è¯Ī
    -0.09
    ä¸įå¾Ĺ转载
    -0.09
    POSITIVE LOGITS
    0.13
    onnement
    0.11
    iful
    0.10
    onne
    0.09
    gone
    0.09
    -mouth
    0.09
    amaha
    0.09
    esian
    0.09
    wide
    0.09
    ious
    0.09
    Activations Density 0.011%

    No Known Activations