© 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. 36052
    Prev
    Next
    INDEX
    Explanations

    http://digitalcommons.law.villanova.edu/

    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
    é¦Ĵ
    -0.09
    çĶij
    -0.09
    è°¤
    -0.09
    าะ
    -0.08
    å·¡
    -0.08
    eus
    -0.08
    sst
    -0.08
    èĨĿ
    -0.08
    侪
    -0.08
     somehow
    -0.08
    POSITIVE LOGITS
    éĵİ
    0.09
     scape
    0.09
    åħīå½±
    0.08
    inality
    0.08
    çķĻä½ı
    0.08
    æĬķèµĦé¡¹çĽ®
    0.08
    TOR
    0.08
    æģ©
    0.07
    æĶ¶åī²
    0.07
    å¦ĤæľŁ
    0.07
    Activations Density 0.070%

    No Known Activations