© 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. 33315
    Prev
    Next
    INDEX
    Explanations

    ad hoc networks or rolling explanations

    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
    odef
    -0.08
    åķ¸
    -0.08
    æĸ°å¹´
    -0.08
    elts
    -0.08
    hover
    -0.08
    æĺ±
    -0.08
    åİħ
    -0.08
    енко
    -0.07
     Tap
    -0.07
    æĮ¯åħ´
    -0.07
    POSITIVE LOGITS
     ad
    0.12
    åİŁåĪĽ
    0.10
    è¿Ń
    0.10
    æ°ijçĶ¨
    0.10
    éĢ
    0.09
    临æŶ
    0.09
     hoc
    0.09
    以人为
    0.09
    绾
    0.08
    é£İ
    0.08
    Activations Density 0.060%

    No Known Activations