© 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. 48399
    Prev
    Next
    INDEX
    Explanations

    rebuilding and reconstruction

    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
    ennen
    -0.09
    éķ¿å¯¿
    -0.08
    æľīæľºä¼ļ
    -0.08
    cade
    -0.08
    ä¸Ģå¤ľ
    -0.08
    éģĹ产
    -0.08
    elsen
    -0.08
    iba
    -0.08
    apult
    -0.08
    å¥ĩæĢª
    -0.08
    POSITIVE LOGITS
    ä¸İåıijå±ķ
    0.13
    ensburg
    0.09
    æį¢ä¸ª
    0.09
    çĬĬ
    0.09
    uw
    0.09
    edException
    0.09
    rive
    0.09
    ing
    0.09
    LATED
    0.08
    ä¹ĭè·¯
    0.08
    Activations Density 0.016%

    No Known Activations