© 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. 53413
    Prev
    Next
    INDEX
    Explanations

    replication

    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
     turb
    -0.09
    ä¸įå¤ļ
    -0.09
    åĽŀåºĶ
    -0.09
    .kernel
    -0.09
    _GRA
    -0.08
    æīİå®ŀ
    -0.08
    iline
    -0.08
    åŃ£
    -0.08
    æ¿Ģ
    -0.08
    éħ·
    -0.08
    POSITIVE LOGITS
    éĢŁåº¦å¿«
    0.09
    çĿ«æ¯Ľ
    0.09
    çĭ¸
    0.09
    å½ĵæĻļ
    0.09
     ÑĤеÑħнолог
    0.09
    é³£
    0.09
    éŀį
    0.09
    çµ®
    0.09
    å«ģç»Ļ
    0.09
    赶åĪ°
    0.09
    Activations Density 0.161%

    No Known Activations