© 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. 32804
    Prev
    Next
    INDEX
    Explanations

    Henry followed by a name

    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
    ../../../
    -0.14
    Ùģار
    -0.10
    ä½ķåĨµ
    -0.09
    _detach
    -0.09
    èģĶç³»æĪij们
    -0.09
    -envelope
    -0.09
    ignal
    -0.09
    ا
    -0.09
    åİ¥
    -0.09
    ging
    -0.09
    POSITIVE LOGITS
    Ùħا
    0.11
    aceous
    0.10
    ials
    0.10
    /disable
    0.10
    paces
    0.10
    æªĶ
    0.09
    icient
    0.09
    æ¶ķ
    0.09
    rist
    0.09
    ine
    0.09
    Activations Density 0.011%

    No Known Activations