© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38378
    Prev
    Next
    INDEX
    Explanations

    husky voice or monotone voice

    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
    çĶŁåij½çļĦ
    -0.10
    實æĸ½
    -0.09
    nam
    -0.09
    пÑĥÑĤ
    -0.09
    sic
    -0.08
    åĬŁè¯¾
    -0.08
    çĶŁåij½
    -0.08
    åħ¶æ¬¡
    -0.08
    ä»ĸå¦Ī
    -0.08
    åIJĦç§įåIJĦæł·
    -0.08
    POSITIVE LOGITS
    令人
    0.09
    aris
    0.09
    çĥ
    0.09
    带æĿ¥çļĦ
    0.09
    æīĢ带æĿ¥çļĦ
    0.08
    éģĩåĪ°
    0.08
    æµı
    0.08
    éħįä¸Ĭ
    0.08
    ä¸ŃåIJ«æľī
    0.08
    _POLL
    0.08
    Activations Density 0.081%

    No Known Activations