© 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. 2814
    Prev
    Next
    INDEX
    Explanations

    no X

    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
    ENO
    -0.09
    åĩłå¼ł
    -0.09
     undert
    -0.08
    ä¸Ģæīĭ
    -0.08
    ä¸ĢåłĨ
    -0.08
    ä¸Ģå¼ł
    -0.08
    ä¸įå°ij
    -0.08
    å¹´ä¸ŃåĽ½
    -0.08
    _Des
    -0.08
    踯
    -0.08
    POSITIVE LOGITS
    éĤ£ä¹Ī容æĺĵ
    0.12
    iable
    0.10
    å¡ij
    0.09
    éĻ¶
    0.09
    iams
    0.09
    御
    0.09
    aims
    0.09
    åıijæĮ¥ä½ľçĶ¨
    0.09
    æĮĤçīĮ
    0.09
     Lub
    0.09
    Activations Density 0.036%

    No Known Activations