© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10739
    Prev
    Next
    INDEX
    Explanations

    pump and fluid mechanics

    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
    åĪĩéĻ¤
    -0.09
    ç¾ģ
    -0.08
    éļıæīĭ
    -0.08
    篦
    -0.08
    9
    -0.08
    çļĦç¡®æĺ¯
    -0.08
    клÑİÑĩа
    -0.08
    åıijçĥ§
    -0.08
    cce
    -0.08
    éĴī
    -0.08
    POSITIVE LOGITS
    æ³µ
    0.10
    æİĸ
    0.10
     pump
    0.09
    æľºæŀĦ
    0.09
    æijĩ
    0.09
    åİĭåĬĽ
    0.09
    æ©Łæ§ĭ
    0.09
    åĶ§
    0.09
    ç«Ń
    0.09
    _traits
    0.09
    Activations Density 0.149%

    No Known Activations