© 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. 32941
    Prev
    Next
    INDEX
    Explanations

    guinea pig

    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
    æ´¥
    -0.10
    å¥ĩå¼Ĥ
    -0.09
    æ··ä¹±
    -0.08
    æ±ģ
    -0.08
    orean
    -0.08
    -offs
    -0.08
    éļ¶
    -0.08
    æĪIJ为ä¸ĢåIJį
    -0.08
    ones
    -0.08
    (es
    -0.07
    POSITIVE LOGITS
    媳
    0.09
    驳
    0.09
    inand
    0.09
    à¹Ħหว
    0.09
    åıĺåİĭ
    0.09
    æĸ°å½¢åĬ¿
    0.09
    Parms
    0.09
    åıĹä¼Ĺ
    0.09
    大ä¼Ĺ
    0.09
    å¾Ĺèµ·
    0.09
    Activations Density 0.007%

    No Known Activations