© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11479
    Prev
    Next
    INDEX
    Explanations

    customer needs and demands

    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
    以人æ°ij
    -0.09
    满äºĨ
    -0.09
    tin
    -0.09
    çŃīå¥ĸ
    -0.09
    çļĦæĬķèµĦ
    -0.09
    çļĦè®¤çŁ¥
    -0.09
    ÑģÑĤо
    -0.09
    .sg
    -0.09
    agog
    -0.09
    西路
    -0.09
    POSITIVE LOGITS
    çī¹å®ļ
    0.12
    åħ·ä½ĵ
    0.10
    Specific
    0.09
     Specific
    0.09
    ä»İ容
    0.09
    å¤ĩ
    0.09
     specific
    0.08
    ä¸Ģç¬ij
    0.08
    æĸ°å½¢åĬ¿ä¸ĭ
    0.08
    诡
    0.08
    Activations Density 0.069%

    No Known Activations