© 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. 54510
    Prev
    Next
    INDEX
    Explanations

    like it

    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
    iero
    -0.08
    æ¹
    -0.08
    åĵ§
    -0.08
    ongs
    -0.08
    çī¹çĤ¹æĺ¯
    -0.08
    æĺł
    -0.08
    åı¯è°ĵ
    -0.08
    amel
    -0.08
    å±Ī
    -0.08
    å¾Ģå¾Ģæĺ¯
    -0.08
    POSITIVE LOGITS
    ä¼¼çļĦ
    0.11
    ä½Ĩå®ŀéĻħä¸Ĭ
    0.11
     somehow
    0.11
    ä¸įåºĶ该
    0.10
    ctl
    0.10
    åĵ¥ä¼¦
    0.10
    antha
    0.09
    æŁIJç§į
    0.09
    éĢıæĺİ
    0.09
    æĹłå½¢
    0.09
    Activations Density 0.077%

    No Known Activations