© 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. 30972
    Prev
    Next
    INDEX
    Explanations

    voice and throat sounds

    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
     pref
    -0.10
     Pref
    -0.09
    Pref
    -0.09
    mant
    -0.09
    è¹Ī
    -0.09
    æ³ķåħ°
    -0.09
    step
    -0.08
    èĮŃ
    -0.08
    pref
    -0.08
    å¼ĢçĿĢ
    -0.08
    POSITIVE LOGITS
    åĹĵåŃIJ
    0.21
    åĹĵ
    0.21
    åĸīåĴĻ
    0.17
     voice
    0.16
    åĸī
    0.16
     голоÑģ
    0.15
    Voice
    0.14
     throat
    0.13
    voice
    0.13
     Voice
    0.13
    Activations Density 0.088%

    No Known Activations