© 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. 38455
    Prev
    Next
    INDEX
    Explanations

    water filtration and supply

    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
    ington
    -0.10
    .ev
    -0.09
    èĿĩ
    -0.09
    ä¹ł
    -0.09
    æŃ»èĢħ
    -0.09
     tent
    -0.09
    çĦ°
    -0.09
    .ptr
    -0.09
    家å±ŀ
    -0.09
    殪
    -0.09
    POSITIVE LOGITS
    涧
    0.11
    æ´ģ
    0.10
    æ³ī
    0.10
    gent
    0.10
    è§Ħ
    0.09
    èĵĦ
    0.09
    æ½Ķ
    0.09
    ÙĨÙĤ
    0.09
    鬣
    0.09
    çĸ¯
    0.09
    Activations Density 0.082%

    No Known Activations