© 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. 18164
    Prev
    Next
    INDEX
    Explanations

    Disney films and characters

    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
    vä
    -0.09
    èµĦ
    -0.09
    beans
    -0.09
    大家éĥ½åľ¨
    -0.09
    éªļæī°
    -0.09
    楼å±Ĥ
    -0.08
    è¢Ń
    -0.08
     bitten
    -0.08
    èĻĽ
    -0.08
    Beans
    -0.08
    POSITIVE LOGITS
    éĩIJ
    0.10
    åİĺ
    0.09
    uyo
    0.09
    ä¾Ķ
    0.09
    spir
    0.09
    é¤IJ
    0.09
    éĵŁ
    0.08
    迪士尼
    0.08
    æĬĽå¼ĥ
    0.08
    .COL
    0.08
    Activations Density 0.025%

    No Known Activations