© 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. 49699
    Prev
    Next
    INDEX
    Explanations

    and and

    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
    åĨĻçĿĢ
    -0.09
    æĥłåıĬ
    -0.09
    æį¢æĿ¥
    -0.09
    åħĭæĭī
    -0.08
    åıĪèĥ½
    -0.08
    è§ģè¯ģ
    -0.08
    å¦ĤæľŁ
    -0.08
    åĩºåĵģ
    -0.08
    峡
    -0.08
     Tak
    -0.08
    POSITIVE LOGITS
     коÑĤоÑĢаÑı
    0.13
     yang
    0.10
     коÑĤоÑĢ
    0.10
     اÙĦتÙī
    0.10
     اÙĦتÙĬ
    0.10
     коÑĤоÑĢÑĭй
    0.10
    èĮī
    0.09
    Ñģи
    0.09
    æĻ·
    0.09
    çŃ¹
    0.09
    Activations Density 0.593%

    No Known Activations