© 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. 2162
    Prev
    Next
    INDEX
    Explanations

    year spells

    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
     Ñģобой
    -0.09
    æĢª
    -0.09
    æ¯ı次éĥ½
    -0.09
     familiar
    -0.08
    _WRAPPER
    -0.08
    cher
    -0.08
    åīįæĸ¹
    -0.08
    _wrapper
    -0.08
     dig
    -0.08
    æŃ»äºĨ
    -0.08
    POSITIVE LOGITS
    åĩłå¹´
    0.12
    å¤ı天
    0.12
    ä¸įä¹ħ
    0.12
    æŶåĢĻ
    0.10
    ä¸Ģ段æŶéĹ´
    0.10
     years
    0.10
    åīįåĩłå¹´
    0.10
    /bower
    0.10
    åIJİæľŁ
    0.10
    å¤ıåŃ£
    0.10
    Activations Density 0.190%

    No Known Activations