© 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. 17059
    Prev
    Next
    INDEX
    Explanations

    audio quality

    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
    éķľå¤´
    -0.10
    æĬĬæīĭ
    -0.09
    æµĭç»ĺ
    -0.09
    çĻ½è¡£
    -0.08
     ÑĩеÑĢ
    -0.08
    глÑıд
    -0.08
    表éĿ¢
    -0.08
    笨
    -0.08
    Pixels
    -0.08
    éĢ¡
    -0.08
    POSITIVE LOGITS
    å£°éŁ³
    0.17
    çļĦå£°éŁ³
    0.14
    éŁ³åĵį
    0.14
    å½ķéŁ³
    0.13
     sound
    0.13
    ä¸ĢåIJ¬
    0.12
    éŁ³é¢ij
    0.12
     sounds
    0.12
    èĢ³æľµ
    0.12
    éŁ³
    0.12
    Activations Density 0.113%

    No Known Activations