© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20093
    Prev
    Next
    INDEX
    Explanations

    may well be

    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
    æĸ¹åı¯
    -0.09
    æł¼å¤ĸ
    -0.08
     dam
    -0.08
    éĢļ常
    -0.08
    tu
    -0.07
    æĪij对
    -0.07
    nip
    -0.07
    çĶŁæĢķ
    -0.07
    afen
    -0.07
    amu
    -0.07
    POSITIVE LOGITS
    å±¹
    0.10
    åħ¥èĤ¡
    0.10
    strap
    0.10
    èĤ±
    0.09
    ä¼ļéķ¿
    0.09
    ®
    0.09
    endon
    0.09
    æ·Ļ
    0.09
    IOR
    0.09
    .authorization
    0.09
    Activations Density 0.004%

    No Known Activations