© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1225
    Prev
    Next
    INDEX
    Explanations

    acoustic phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    routine
    -0.29
    æ°°
    -0.28
    å¸ľ
    -0.25
     routine
    -0.25
    çīĪæľ¬
    -0.23
    åıªä¸įè¿ĩ
    -0.22
    åIJĮèĥŀ
    -0.22
    åĨĴçĿĢ
    -0.22
     SOC
    -0.22
    resume
    -0.22
    POSITIVE LOGITS
    åľºé¦Ĩ
    0.32
    éĢļé£İ
    0.30
    éŨçªĹ
    0.29
    èµ°å»Ĭ
    0.28
     ceilings
    0.28
    éŁ³åĵį
    0.28
     vocal
    0.27
    .Sound
    0.27
    /music
    0.27
     damp
    0.26
    Activations Density 0.011%

    No Known Activations