© 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. 1573
    Prev
    Next
    INDEX
    Explanations

    body parts and ownership

    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
    äºĨå¤ļå°ij
    -0.10
    好äºĭ
    -0.10
     jet
    -0.10
    天涯
    -0.10
    jet
    -0.09
    æĴµ
    -0.09
    ä¸įçŁ¥ä¸į
    -0.09
    åħ¨æĿij
    -0.09
    çľĭæ¸ħ
    -0.09
    åĩºè·¯
    -0.09
    POSITIVE LOGITS
    éĢĤå½ĵ
    0.09
    icus
    0.09
    æľ¬è½®
    0.09
    å¹²æī°
    0.08
    èħij
    0.08
    èĥĮéĥ¨
    0.08
    æł¸å¿ĥ
    0.08
    zon
    0.08
    azon
    0.08
    ecz
    0.08
    Activations Density 0.023%

    No Known Activations