© 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. 10913
    Prev
    Next
    INDEX
    Explanations

    inner lining

    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
    åĩŃä»Ģä¹Ī
    -0.09
    饴
    -0.09
    eka
    -0.09
    çªģçł´åı£
    -0.09
    ines
    -0.09
    纵横
    -0.08
     ca
    -0.08
    ä¸ĢåŃĹ
    -0.08
    éªĪ
    -0.08
    oke
    -0.08
    POSITIVE LOGITS
     Schultz
    0.09
    çĶŁäº§æĢ»åĢ¼
    0.09
     Cathedral
    0.09
    å·´æĭī
    0.09
    chte
    0.09
    URAL
    0.08
    itial
    0.08
    ظ
    0.08
     INCLUDED
    0.08
    帼
    0.08
    Activations Density 0.009%

    No Known Activations