© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53135
    Prev
    Next
    INDEX
    Explanations

    musical terms and structure

    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
    è§Ħ
    -0.09
    ç¿ķ
    -0.09
    å®ŀåĬĽ
    -0.09
    éħĭ
    -0.09
    edList
    -0.09
    æıIJä¾Ľä¼ĺè´¨
    -0.08
    没æľīå¿ħè¦ģ
    -0.08
    æľīæĿ¡ä»¶çļĦ
    -0.08
    æĹ¢çĦ¶
    -0.08
    çĨ¬
    -0.08
    POSITIVE LOGITS
    éľŃ
    0.09
    äºĮ人
    0.09
     Checked
    0.08
    æ½®
    0.08
    ipc
    0.08
    Facing
    0.08
    _ctr
    0.08
     tub
    0.08
    éĩįä¸Ń
    0.08
     retrie
    0.08
    Activations Density 0.080%

    No Known Activations