© 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. 62681
    Prev
    Next
    INDEX
    Explanations

    optical surveys

    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
    èĪŁ
    -0.11
    å§ij
    -0.11
    æĭ®
    -0.10
    èī¯å¿ĥ
    -0.10
    å¶Ĥ
    -0.09
    #line
    -0.09
    ç»ıæµİä½ĵ
    -0.08
    umbo
    -0.08
    ollo
    -0.08
    _tensors
    -0.08
    POSITIVE LOGITS
    åŁĭ
    0.10
    ä¼Ĭæĭī
    0.10
     Zucker
    0.09
    iat
    0.08
    æįº
    0.08
    å¾Īå¿«
    0.08
    åīľ
    0.08
    åĬ¨çĶŁæĪIJ
    0.08
    ä½İæĪIJæľ¬
    0.08
    _MOV
    0.08
    Activations Density 0.102%

    No Known Activations