© 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. 34135
    Prev
    Next
    INDEX
    Explanations

    what to say or do

    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
    解åĨ³éĹ®é¢ĺ
    -0.09
    sters
    -0.09
    ãģ£ãģ¨
    -0.09
     ê°ĢëĬ¥íķľ
    -0.08
    åĵģå¾·
    -0.08
    éĢŀ
    -0.08
    åĨ³èĥľ
    -0.08
    åİī
    -0.08
    OLVE
    -0.08
    LOUR
    -0.08
    POSITIVE LOGITS
    åIJĥçļĦ
    0.11
    åģļçļĦ
    0.10
    è¿Ń
    0.09
    å®Įç¾İçļĦ
    0.09
    irse
    0.09
    åģļ强
    0.09
    åĵī
    0.09
    ราว
    0.09
    getter
    0.09
    æ¸ħæĸ°
    0.08
    Activations Density 0.016%

    No Known Activations