© 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. 4395
    Prev
    Next
    INDEX
    Explanations

    Staff, Authors, Team

    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
    åĿļå®ļä¸į移
    -0.10
    åı°éĺ¶
    -0.10
    åıįæĺł
    -0.09
    æįŁ
    -0.09
    åĵ²
    -0.09
    èĪįå¾Ĺ
    -0.09
    èĢģçĪ·
    -0.08
    åĵ¥ä»¬
    -0.08
    æĻ®æĥł
    -0.08
    æĹłç§ģ
    -0.08
    POSITIVE LOGITS
    å¸ĥ
    0.09
    RelativeTo
    0.08
    绪
    0.08
    sav
    0.08
     lắng
    0.08
    owie
    0.08
    åįĴ
    0.08
    ellig
    0.08
    éĩİå¤ĸ
    0.08
    avit
    0.08
    Activations Density 0.005%

    No Known Activations