© 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. 11429
    Prev
    Next
    INDEX
    Explanations

    when

    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
     backgroundImage
    -0.09
    fits
    -0.08
    avn
    -0.08
    ä¼ĺæĥłæĶ¿çŃĸ
    -0.08
    Scalars
    -0.08
    жи
    -0.08
    æĻ®éĢļè¯Ŀ
    -0.08
    Äĥn
    -0.08
    åı¯ä»¥éĢļè¿ĩ
    -0.08
    ivr
    -0.08
    POSITIVE LOGITS
     when
    0.12
    when
    0.11
     когда
    0.11
     khi
    0.10
     gdy
    0.10
    ä½ķæŶ
    0.10
    壮
    0.10
     ׼ש×Ķ
    0.10
    æľī人
    0.10
    æįį
    0.09
    Activations Density 0.094%

    No Known Activations