© 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. 63290
    Prev
    Next
    INDEX
    Explanations

    exactly what

    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
    å®Ľ
    -0.10
    峡
    -0.09
    èļĬ
    -0.09
    å±ķè§Ī
    -0.09
    åĴĭ
    -0.09
    è£ħéħį
    -0.09
    aroo
    -0.09
    æĭĽçĶŁ
    -0.08
     Census
    -0.08
    åIJĮåѦ
    -0.08
    POSITIVE LOGITS
    æģ°æģ°
    0.15
    æŃ£æĺ¯
    0.15
    ä¹ŁæŃ£æĺ¯
    0.12
    è¿ĻäºĽéĹ®é¢ĺ
    0.12
    æŃ£å¥½
    0.11
     wÅĤaÅĽnie
    0.11
     exactly
    0.11
    ä¸İæѤ
    0.11
    è¿Ļ个éĹ®é¢ĺ
    0.11
    æģ°å¥½
    0.10
    Activations Density 0.044%

    No Known Activations