© 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. 49018
    Prev
    Next
    INDEX
    Explanations

    porting from one format to another

    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
    è±IJ
    -0.10
    æĨ¾
    -0.09
    éļĻ
    -0.09
    æĭĴ
    -0.09
    è´Ńç½®
    -0.08
    åł°
    -0.08
    å¡«è¡¥
    -0.08
    太å°ij
    -0.08
    åĪ¶è®¢
    -0.08
    ä½ĺ
    -0.08
    POSITIVE LOGITS
    åıĺæĪIJ
    0.12
    åºĶçĶ¨äºİ
    0.11
    éĢĤçĶ¨äºİ
    0.11
    éħįä¸Ĭ
    0.11
    åģļæĪIJ
    0.11
    æį¢æĪIJ
    0.11
    åıĺå¾ĹæĽ´
    0.11
    åıĺæĪIJäºĨ
    0.10
    移åĪ°
    0.10
    æIJ¬åĪ°
    0.10
    Activations Density 0.177%

    No Known Activations