© 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. 50555
    Prev
    Next
    INDEX
    Explanations

    nature of that company

    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
    èĨº
    -0.09
    .Claims
    -0.08
    æĺ¯çľŁçļĦ
    -0.08
     therefore
    -0.08
     Mant
    -0.08
    sole
    -0.08
     обÑĭ
    -0.07
     Cros
    -0.07
    ä¼Ĭæĭī
    -0.07
    tok
    -0.07
    POSITIVE LOGITS
    æŃ£æĺ¯
    0.12
     przecież
    0.11
    æģ°æģ°
    0.11
    ä¹ŁæŃ£æĺ¯
    0.10
    æģ°
    0.10
    æģ°å¥½
    0.10
    æŃ£å¥½
    0.10
    æľ¬èº«å°±æĺ¯
    0.10
    ç¼Ķ
    0.10
    æѤåĪ»
    0.09
    Activations Density 0.113%

    No Known Activations