© 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. 32368
    Prev
    Next
    INDEX
    Explanations

    extracting date components

    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
    å¥łå®ļäºĨ
    -0.09
    çĻ£
    -0.09
    æ·±å¤ľ
    -0.08
     NDEBUG
    -0.08
     PATCH
    -0.08
    pector
    -0.08
    å¾®è§Ĥ
    -0.08
     raw
    -0.08
    net
    -0.08
    resse
    -0.08
    POSITIVE LOGITS
    ä¿ļ
    0.09
    éķ¶åµĮ
    0.09
    ucc
    0.09
    SENT
    0.08
     Volt
    0.08
    ä½ĵåĨħ
    0.08
    çķı
    0.08
    ãĥ¡ãĥ³
    0.08
    RCT
    0.08
    æĬ±çĿĢ
    0.08
    Activations Density 0.582%

    No Known Activations