© 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. 17344
    Prev
    Next
    INDEX
    Explanations

    craniometry tomography

    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
    å¾Ģä¸ĭ
    -0.10
    æ§ģ
    -0.09
    ä¸ĵ线
    -0.09
    iac
    -0.09
    åį¿
    -0.08
    å¾Ģ
    -0.08
    å¼Ģåĩº
    -0.08
    é¢Ľ
    -0.08
    带ä¸Ĭ
    -0.08
    解æĶ¾
    -0.08
    POSITIVE LOGITS
    åĵŃ
    0.15
    çľ¼æ³ª
    0.13
    åĵŃäºĨ
    0.12
    ç½¢
    0.12
    åĵŃæ³£
    0.12
    èĢį
    0.12
    å§Ķå±Ī
    0.11
     Cry
    0.11
    泪水
    0.11
    cry
    0.11
    Activations Density 0.047%

    No Known Activations