© 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. 53545
    Prev
    Next
    INDEX
    Explanations

    count for

    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
    åĮķ
    -0.10
    ALES
    -0.09
    æīĢèĥ½
    -0.09
    quito
    -0.09
    Bloc
    -0.09
    IFIED
    -0.09
    çĨł
    -0.08
    èĹIJ
    -0.08
    athed
    -0.08
    éĩįè¦ģæĮĩ示
    -0.08
    POSITIVE LOGITS
    ä¸įç®Ĺ
    0.14
    enance
    0.11
     counts
    0.10
    ç®Ĺæĺ¯
    0.09
    counts
    0.09
    æº
    0.08
    éĢļè¡Į
    0.08
    å°ıå¾®
    0.08
    æĸ¯åŁº
    0.08
    ä¹Łç®Ĺ
    0.08
    Activations Density 0.023%

    No Known Activations