© 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. 11055
    Prev
    Next
    INDEX
    Explanations

    sturdy and slender physical descriptions

    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
    ting
    -0.11
    apur
    -0.10
    éı¡
    -0.09
    åĽ½åĢº
    -0.09
    INATION
    -0.08
    andro
    -0.08
    åĬĽäºī
    -0.08
    æ·±æ¸Ĭ
    -0.08
    ation
    -0.08
    inations
    -0.08
    POSITIVE LOGITS
     enough
    0.11
    åı¯éĿłçļĦ
    0.10
    ä¸Ģçľĭ
    0.10
    loom
    0.10
    hold
    0.10
    ä¸įéĶĻçļĦ
    0.10
     Enough
    0.09
    Enough
    0.09
    ä¸Ģä¸ĭ
    0.09
    ayload
    0.09
    Activations Density 0.004%

    No Known Activations