© 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. 48865
    Prev
    Next
    INDEX
    Explanations

    find out how

    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
    ä¾Ī
    -0.08
    è¶Ł
    -0.08
    eel
    -0.08
    主è¦ģæľī
    -0.08
    æŧ
    -0.08
    åŀĴ
    -0.08
    鸽
    -0.08
    åľĪåŃIJ
    -0.08
     Dos
    -0.08
    -formed
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īæĺ¯
    0.10
    æĽ´å¤ļä¿¡æģ¯
    0.10
    antor
    0.09
    ledged
    0.09
    roscope
    0.09
    羣缸
    0.09
    åĬ©çIJĨ
    0.08
    çīĪæĿĥå½Ĵ
    0.08
    seite
    0.08
    urdy
    0.08
    Activations Density 0.007%

    No Known Activations