© 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. 55523
    Prev
    Next
    INDEX
    Explanations

    perfumed, perfector, perfused

    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
    åĦĺ
    -0.09
    zelf
    -0.09
    orem
    -0.09
    çĿĽ
    -0.08
    ä¸Ģæī¹
    -0.08
    ocs
    -0.08
    ood
    -0.08
    说çļĦæĺ¯
    -0.08
    uffers
    -0.08
    讽
    -0.08
    POSITIVE LOGITS
    ëĿ¼ëıĦ
    0.09
    åŃĽ
    0.09
    ictim
    0.09
    oland
    0.09
    stood
    0.09
    à¹Ħà¸Ĺย
    0.09
    èĤ²åĦ¿
    0.09
    emu
    0.09
    brains
    0.09
    ault
    0.09
    Activations Density 0.005%

    No Known Activations