© 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. 62763
    Prev
    Next
    INDEX
    Explanations

    went on

    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
    tern
    -0.10
    迹
    -0.10
    .Formatter
    -0.10
    触åıĬ
    -0.09
    ä¹ł
    -0.09
    _ORIENTATION
    -0.09
    /OR
    -0.09
    æĦıè§ģåıįé¦Ī
    -0.09
    eof
    -0.09
    onga
    -0.09
    POSITIVE LOGITS
    å¿ĥ缮
    0.09
    ä¸įèµ·
    0.09
    å¿ĥ缮ä¸Ń
    0.08
    osen
    0.08
    jets
    0.08
    .exe
    0.08
    dispatch
    0.08
    éŃĶ鬼
    0.08
    å½ĵå¹´
    0.08
    ç»ıæŁ¥
    0.08
    Activations Density 0.010%

    No Known Activations