© 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. 53817
    Prev
    Next
    INDEX
    Explanations

    sounds and their descriptors

    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
    她æĺ¯
    -0.09
    å°Ħæīĭ
    -0.09
    å°±æĺ¯è¿Ļæł·
    -0.09
    姥
    -0.08
    æĴĴ
    -0.08
    asters
    -0.08
    manifest
    -0.08
    æŃª
    -0.08
    nf
    -0.08
    çªł
    -0.08
    POSITIVE LOGITS
    声åĵį
    0.23
    çļĦå£°éŁ³
    0.23
    å£°éŁ³
    0.22
    ä¹ĭ声
    0.21
    声
    0.20
     sounds
    0.20
     sound
    0.20
    åĵį
    0.18
    èģ²éŁ³
    0.18
    èģ²
    0.17
    Activations Density 0.058%

    No Known Activations