© 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. 23872
    Prev
    Next
    INDEX
    Explanations

    air flow and ventilation

    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
    亲èĩª
    -0.10
    æľĢåıĹ
    -0.09
    ä»ĺè´¹
    -0.09
     sign
    -0.08
    æĥ³çĿĢ
    -0.08
    ẩu
    -0.08
    éľ²
    -0.08
    åīįåı°
    -0.08
    ä¹ĭ人
    -0.08
     Wal
    -0.08
    POSITIVE LOGITS
    éĢļé£İ
    0.13
    æķ£çĥŃ
    0.10
    _fre
    0.10
    èĩªçĶ±
    0.10
     ventilation
    0.10
    æµģéĢļ
    0.10
    .fre
    0.09
    æĸ¯å¡Ķ
    0.09
     pers
    0.09
     Ñģвобод
    0.09
    Activations Density 0.042%

    No Known Activations