© 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. 52845
    Prev
    Next
    INDEX
    Explanations

    seat cushion or padding

    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
    thal
    -0.09
    åĢ¼å¾Ĺåħ³æ³¨
    -0.08
    æ²ī
    -0.08
    ListModel
    -0.08
     pont
    -0.08
    æ³¢
    -0.08
    串
    -0.08
     trivial
    -0.07
    ä¿Ŀå®Ī
    -0.07
    ç¿»
    -0.07
    POSITIVE LOGITS
    èħIJè´¥
    0.10
    .LoggerFactory
    0.10
    æĹ©æĻļ
    0.10
    (da
    0.09
    æĺŁæĺŁ
    0.09
    对åħ¬åı¸
    0.09
    交éĢļ
    0.09
    æ²»çĸĹæĸ¹æ³ķ
    0.09
    森æŀĹ
    0.09
    çīĿ
    0.09
    Activations Density 0.090%

    No Known Activations