© 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. 35526
    Prev
    Next
    INDEX
    Explanations

    ear and hearing

    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
    çĪª
    -0.09
    åĴ³
    -0.09
    åĬĽéĩı
    -0.09
    çĻ«
    -0.08
    信念
    -0.08
    æIJŃä¹ĺ
    -0.08
    åĢĴ
    -0.08
    çģ¯çģ«
    -0.08
    éĺ´
    -0.08
    illin
    -0.08
    POSITIVE LOGITS
    åIJ¬åĬĽ
    0.21
    èĢ³
    0.20
    èĢ³æľµ
    0.19
    åIJ¬å¾Ĺ
    0.19
     hearing
    0.19
    åIJ¬
    0.18
    èģĨ
    0.17
    èģ½
    0.16
    èĢ³æľº
    0.16
    Listening
    0.16
    Activations Density 0.105%

    No Known Activations