© 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. 18399
    Prev
    Next
    INDEX
    Explanations

    stranger who, daughter who

    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
    OrUpdate
    -0.10
    æĸ°ä¸ī
    -0.10
    å¥ĩ迹
    -0.10
    åĩºéģĵ
    -0.09
    .solution
    -0.09
    è¹Ī
    -0.09
    SED
    -0.09
    泫
    -0.09
    LAY
    -0.08
    Ord
    -0.08
    POSITIVE LOGITS
    举æŃ¢
    0.11
    nish
    0.10
    åįģ足
    0.10
    æĮijåīĶ
    0.10
    å¸ĤåľºéľĢæ±Ĥ
    0.09
    ä»İä¸Ń
    0.09
    ï¼Īç¬ij
    0.09
    åĪģ
    0.09
    浪
    0.08
    isms
    0.08
    Activations Density 0.078%

    No Known Activations