© 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. 33729
    Prev
    Next
    INDEX
    Explanations

    entries, contests, and drawings

    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
    ä¸Ģç¬Ķ
    -0.09
    åı¥
    -0.09
    rÃŃ
    -0.09
    chia
    -0.08
    ivirus
    -0.08
    款
    -0.08
     microseconds
    -0.08
    æŀ
    -0.08
    åijIJ
    -0.08
    çĶ³è´Ń
    -0.08
    POSITIVE LOGITS
    imentos
    0.10
    为ä¹ĭ
    0.10
    ä¹ĭæĺŁ
    0.10
    imento
    0.10
    å¿Ļ
    0.09
    ENTS
    0.09
    .eof
    0.09
    orth
    0.09
    æľīäºĨ
    0.09
    abin
    0.09
    Activations Density 0.011%

    No Known Activations