© 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. 38944
    Prev
    Next
    INDEX
    Explanations

    now that

    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
    CESS
    -0.09
    trim
    -0.08
    ä¸Ģæ³¢
    -0.08
    SV
    -0.08
    zug
    -0.08
    çļĦæĢ§æł¼
    -0.08
    åĪļæīį
    -0.08
    ully
    -0.08
    æľ¬æľŁ
    -0.08
    åĨľä¸ļ大åѦ
    -0.08
    POSITIVE LOGITS
    çļ®
    0.10
    ÑıÑī
    0.10
    åģļä»Ģä¹Ī
    0.09
    å¾ķ
    0.09
    adays
    0.09
    üm
    0.09
    UMB
    0.09
    owie
    0.08
    åij½åIJį为
    0.08
    \Validation
    0.08
    Activations Density 0.044%

    No Known Activations