© 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. 49454
    Prev
    Next
    INDEX
    Explanations

    cougar, Lion, coumarin, McGregor

    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
    æļĩ
    -0.11
    lessly
    -0.10
    æºIJæºIJ
    -0.09
    aker
    -0.09
    åŁĴ
    -0.09
    reck
    -0.09
     Seal
    -0.09
    æĪŁ
    -0.09
    reich
    -0.08
    ä¹¾åĿ¤
    -0.08
    POSITIVE LOGITS
    .cloudflare
    0.10
    æıIJæĹ©
    0.09
    regor
    0.09
    arness
    0.09
    ustin
    0.09
     Hazard
    0.09
     McGregor
    0.08
    lsen
    0.08
    omed
    0.08
    azine
    0.08
    Activations Density 0.005%

    No Known Activations