© 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. 31878
    Prev
    Next
    INDEX
    Explanations

    words ending in y

    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
    n
    -0.10
    istic
    -0.09
    al
    -0.09
    sWith
    -0.09
    na
    -0.09
    fully
    -0.09
    lie
    -0.09
    éĩįè¦ģæĦıä¹ī
    -0.09
    æĦıä¹ī
    -0.09
    ively
    -0.09
    POSITIVE LOGITS
    NESS
    0.16
     enough
    0.12
    -looking
    0.12
    -haired
    0.11
    Enough
    0.11
    ness
    0.10
    ä¸įåłª
    0.10
     ×ij×Ļ×ķתר
    0.10
     haired
    0.10
    oting
    0.10
    Activations Density 0.078%

    No Known Activations