© 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. 21949
    Prev
    Next
    INDEX
    Explanations

    depressing pedals

    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
    泡泡
    -0.09
    å®ł
    -0.09
    éĩī
    -0.09
    èĮ§
    -0.08
    åĢº
    -0.08
    å··
    -0.08
    è¯Ľ
    -0.08
    ä¹Ĵ
    -0.08
    (*)
    -0.08
    esi
    -0.08
    POSITIVE LOGITS
    è¸ı
    0.15
    踩
    0.11
    ä¸ĢèĦļ
    0.10
    омеÑĢ
    0.10
     пед
    0.10
    åĪ¹è½¦
    0.09
    è¸ıä¸Ĭ
    0.09
     Affero
    0.09
    éta
    0.09
    omi
    0.09
    Activations Density 0.041%

    No Known Activations