© 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. 4269
    Prev
    Next
    INDEX
    Explanations

    few, little, couple of

    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
    äºĨä¸įå°ij
    -0.12
    å¾Ĺå¾Ī好
    -0.11
    好åĩłä¸ª
    -0.11
    ä¸įå°ij
    -0.11
    äºĨä¸Ģåľº
    -0.10
    两ç§į
    -0.10
    两款
    -0.10
    ä¸ī个æĸ¹éĿ¢
    -0.10
    çĿ£åĬŀ
    -0.09
    äºĨä¸Ģç³»åĪĹ
    -0.09
    POSITIVE LOGITS
    åıī
    0.10
    å¢ŀè¿Ľ
    0.09
     ê°
    0.09
    åŃĿ
    0.09
    ahkan
    0.08
    rift
    0.08
     Shutterstock
    0.08
    椽
    0.08
    rear
    0.08
    _IDENTIFIER
    0.08
    Activations Density 0.067%

    No Known Activations