© 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. 61880
    Prev
    Next
    INDEX
    Explanations

    whistle and related 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
    ä¸įåłª
    -0.10
    -ish
    -0.09
    zilla
    -0.09
    è¿Ļä¸ĢçĤ¹
    -0.09
    ish
    -0.09
    ç¡®
    -0.09
    æĢĿæĥ³
    -0.08
     вÑĢемен
    -0.08
    ãģ¹ãģį
    -0.08
    ient
    -0.08
    POSITIVE LOGITS
    ler
    0.11
    mith
    0.10
    å½¹
    0.10
    ively
    0.10
    海岸
    0.09
    tails
    0.09
    .rand
    0.09
    æľīéĹ®é¢ĺ
    0.09
    mill
    0.09
    paralle
    0.08
    Activations Density 0.006%

    No Known Activations