© 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. 62941
    Prev
    Next
    INDEX
    Explanations

    auditory signals and 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
    羣æŃ£åģļåĪ°
    -0.09
    æ¼Ĥæµģ
    -0.09
    øy
    -0.09
     bÄĥng
    -0.09
    åĶ®åIJİ
    -0.09
    å§ļæĺİ
    -0.08
    åıĽ
    -0.08
    prm
    -0.08
    æłī
    -0.08
    æ¼Ĥ
    -0.08
    POSITIVE LOGITS
    éĵĥ
    0.10
    åĺŁ
    0.10
     bell
    0.10
     tone
    0.10
    åĺĢ
    0.09
    鸣
    0.09
    åıij声
    0.09
     beep
    0.09
    å£°éŁ³
    0.09
     tones
    0.09
    Activations Density 0.091%

    No Known Activations