© 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. 50881
    Prev
    Next
    INDEX
    Explanations

    County Metro

    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
    æĽľ
    -0.11
    çĪĨ
    -0.09
    å±ķå¼Ģ
    -0.09
    IENT
    -0.09
    CSR
    -0.09
    人éĹ´
    -0.09
    ĥĿ
    -0.09
    ä¸Ĭåİ»
    -0.08
    .unwrap
    -0.08
     Hir
    -0.08
    POSITIVE LOGITS
    _reserve
    0.09
    绿水
    0.09
    åį¡çīĩ
    0.09
    çĬ¯
    0.09
    æľºæ¢°åĮĸ
    0.09
    涧
    0.09
    -touch
    0.09
     Kü
    0.08
    伤
    0.08
    allon
    0.08
    Activations Density 0.046%

    No Known Activations