© 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. 18674
    Prev
    Next
    INDEX
    Explanations

    children and family

    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
    让èĩªå·±
    -0.10
    æĪIJåŀĭ
    -0.10
    зв
    -0.10
    æĪIJ为ä¸Ģ个
    -0.10
    азв
    -0.09
    ject
    -0.09
    éĵ³
    -0.09
    лÑıÑĢ
    -0.09
    TES
    -0.09
    irez
    -0.09
    POSITIVE LOGITS
    éĩĬ
    0.09
    å¸Ń
    0.09
    éĤ£åıª
    0.08
    è§Ĩè§Ĵ
    0.08
    éĥ¨èIJ½
    0.08
    èį·
    0.08
    _generated
    0.08
    -held
    0.08
    åħij
    0.07
    èĩªåĪ¶
    0.07
    Activations Density 0.026%

    No Known Activations