© 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. 62916
    Prev
    Next
    INDEX
    Explanations

    Spanish words and common legal/copyright terms

    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
    edly
    -0.11
    -flight
    -0.09
    eer
    -0.09
    viously
    -0.09
    ersist
    -0.09
    ä»Ĩ
    -0.08
     Gad
    -0.08
    æ¸İ
    -0.08
     gad
    -0.08
    -images
    -0.08
    POSITIVE LOGITS
    bö
    0.10
    éĻ¬
    0.10
    æģ¤
    0.09
    rz
    0.09
    磾
    0.09
    ting
    0.08
    é£İæ³¢
    0.08
    ìĬĪ
    0.08
    okin
    0.08
    溪
    0.08
    Activations Density 0.004%

    No Known Activations