© 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. 36017
    Prev
    Next
    INDEX
    Explanations

    calculate

    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
    eker
    -0.13
    olis
    -0.12
    fall
    -0.11
    zel
    -0.11
    çĦ¶æĺ¯
    -0.10
     Decay
    -0.09
    holds
    -0.09
    Calculator
    -0.09
    Ìģ
    -0.09
    æĥħåĨµæĿ¥çľĭ
    -0.09
    POSITIVE LOGITS
    culate
    0.10
    ibrate
    0.10
    Ñĩик
    0.10
    adora
    0.09
    ULATE
    0.09
    çļ¿
    0.09
    ä¸ĩåĪĨ
    0.09
    ibrated
    0.09
    enic
    0.09
    ulation
    0.09
    Activations Density 0.034%

    No Known Activations