© 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. 17674
    Prev
    Next
    INDEX
    Explanations

    solving problems

    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
    ICT
    -0.08
    å³°
    -0.08
    ÙĪÙĨØ©
    -0.08
     sulfate
    -0.08
    æĶ¹éĿ©å¼ĢæĶ¾
    -0.07
    Austin
    -0.07
    Wi
    -0.07
    ä¼ģä¸ļåĴĮ
    -0.07
    live
    -0.07
    Membership
    -0.07
    POSITIVE LOGITS
    èĺ§
    0.11
    å®ŀçĶ¨
    0.10
    æĿ¥çĶµ
    0.09
    èĩªæķij
    0.09
    该æ¡Ī
    0.09
    ä¹ŁåĽłæѤ
    0.09
    ouver
    0.08
    å¼łå®¶
    0.08
    ä»İä¸Ń
    0.08
    åıijè´¢
    0.08
    Activations Density 2.060%

    No Known Activations