© 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. 11026
    Prev
    Next
    INDEX
    Explanations

    names ending in -son or -on

    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
    åĽ¾ä¸º
    -0.09
    æĪijä¸įæĥ³
    -0.09
    æ¯ĵ
    -0.09
    åį·
    -0.09
    ICI
    -0.09
    ä¸ĥæĺŁ
    -0.08
    hed
    -0.08
    æ¶Ķ
    -0.08
    pora
    -0.08
    ä¿Ŀå®Ī
    -0.08
    POSITIVE LOGITS
    usta
    0.10
    olec
    0.09
    etheless
    0.09
    åĩºå±Ģ
    0.09
    éľ²
    0.08
    iguous
    0.08
    à´±
    0.08
    åī¥ç¦»
    0.08
    裸
    0.08
    å¹³æĿ¿
    0.08
    Activations Density 0.055%

    No Known Activations