© 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. 21475
    Prev
    Next
    INDEX
    Explanations

    letter to editor or chairman

    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
    éļ¼
    -0.11
    ording
    -0.10
    è¶ĭ
    -0.10
    æİĪ
    -0.09
    å¼Ģåĩº
    -0.09
    æĿ·
    -0.09
    ills
    -0.09
    æµģ失
    -0.09
    è¡ĮæĶ¿æī§æ³ķ
    -0.08
    çĤ¹ç¼Ģ
    -0.08
    POSITIVE LOGITS
    å°Ĭæķ¬
    0.11
    ä¸Ģå°ģ
    0.11
     letter
    0.11
    Dear
    0.11
    -letter
    0.11
    ä¸Ģå°ģä¿¡
    0.11
    Letter
    0.10
     Dear
    0.10
    letter
    0.10
    _letter
    0.09
    Activations Density 0.062%

    No Known Activations