© 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. 4243
    Prev
    Next
    INDEX
    Explanations

    out into

    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
    æĿ¥åĽŀ
    -0.10
    åĽŀæĶ¶
    -0.09
     Transport
    -0.09
     transport
    -0.08
    åľ¨åľ°ä¸Ĭ
    -0.08
    ored
    -0.08
    丼
    -0.08
    æĸ¥
    -0.08
    æĿ¥åİĨ
    -0.08
    ora
    -0.08
    POSITIVE LOGITS
    ndef
    0.10
    ä¸Ģéģĵ
    0.10
    鼩
    0.10
    è·³åĩº
    0.09
    iams
    0.08
     Icons
    0.08
    éĽħ
    0.08
    åĹĴ
    0.08
    gan
    0.08
    lets
    0.08
    Activations Density 0.049%

    No Known Activations