© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53079
    Prev
    Next
    INDEX
    Explanations

    likely to

    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
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.11
    ä¼¼ä¹İ
    -0.10
    ç´¯äºĨ
    -0.10
    nell
    -0.09
    å±ħçĦ¶
    -0.09
    pan
    -0.09
    åħ³éĶ®æĺ¯
    -0.09
    寤
    -0.09
    agt
    -0.09
    ä¿©
    -0.09
    POSITIVE LOGITS
    hood
    0.16
    mente
    0.13
    NESS
    0.12
    åľ¨æľªæĿ¥
    0.11
    LY
    0.11
    ä¸įä¼ļæľī
    0.10
    ìĤ¬íķŃ
    0.10
    -minded
    0.10
    ement
    0.10
    .subplots
    0.10
    Activations Density 0.020%

    No Known Activations