© 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. 1176
    Prev
    Next
    INDEX
    Explanations

    increase or decrease

    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
    åıįå¤į
    -0.09
    å°ļ
    -0.09
    _UNDEFINED
    -0.08
    airo
    -0.08
    ç»ıåİĨäºĨ
    -0.08
     added
    -0.08
    ип
    -0.08
    空æ°Ķ
    -0.08
    ç»Ħç»ĩå¼Ģå±ķ
    -0.08
    çļĦéģĵçIJĨ
    -0.08
    POSITIVE LOGITS
    第ä¸ĢåIJį
    0.09
    åıªåī©
    0.09
    æĺ¯æľī
    0.09
     Pret
    0.08
    åıªåī©ä¸ĭ
    0.08
    äºĭåħ³
    0.08
    缮åīį为æŃ¢
    0.08
    缮çļĦåľ°
    0.08
     tarea
    0.08
    åħ³ä¹İ
    0.08
    Activations Density 0.074%

    No Known Activations