© 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. 11249
    Prev
    Next
    INDEX
    Explanations

    several, awards, companies, stations

    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
    è§Ħ模æľĢ大
    -0.10
    å¤ļä¹Ī
    -0.10
    å®ĿèĹı
    -0.10
    ä¸ĩåįĥ
    -0.10
    amac
    -0.09
    upe
    -0.09
    è¿Ļ个åIJįåŃĹ
    -0.09
    ç¹ģå¿Ļ
    -0.09
     widest
    -0.09
    _SUPER
    -0.09
    POSITIVE LOGITS
    äºĨä¸įå°ij
    0.17
     several
    0.16
    好åĩłä¸ª
    0.15
    诸å¦Ĥ
    0.14
    äºĨ好åĩł
    0.14
    äºĨä¸ĢäºĽ
    0.14
    ä¸įå°ij
    0.14
    Several
    0.13
     Several
    0.13
    ä¸ĢäºĽ
    0.13
    Activations Density 0.341%

    No Known Activations