© 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. 39746
    Prev
    Next
    INDEX
    Explanations

    time periods and durations

    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
    çĻ½å¤©
    -0.10
    è°Ł
    -0.10
    éľ²
    -0.10
    inator
    -0.09
    åħŃåIJĪ
    -0.09
    _thr
    -0.09
    æ¿ĢåĬ±
    -0.09
    åIJĪå½±
    -0.09
    å½ķ
    -0.09
    .pose
    -0.09
    POSITIVE LOGITS
    æľºä¼ļ
    0.14
    çļĦæľºä¼ļ
    0.14
    åĸĺ
    0.11
    æ©Łæľĥ
    0.10
     opportunity
    0.10
    æľŁéĻIJ
    0.10
     chance
    0.10
    åħħè£ķ
    0.10
     opportunities
    0.10
    æľŁ
    0.09
    Activations Density 0.096%

    No Known Activations