© 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. 4856
    Prev
    Next
    INDEX
    Explanations

    Timothy Timothy Timothy

    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
    ä¿£
    -0.10
    åIJįçīĩ
    -0.10
    å°¤åħ¶æĺ¯
    -0.10
    URT
    -0.09
    uide
    -0.09
     ipc
    -0.08
    循
    -0.08
    âĸ½
    -0.08
    åºĦ
    -0.08
    åĿŀ
    -0.08
    POSITIVE LOGITS
    èµŀæī¬
    0.09
    线ä¸ĭ
    0.08
    请éĹ®
    0.08
    lining
    0.08
    ä¸İæѤ
    0.08
    TEGR
    0.08
    亲è¿ij
    0.08
    带æľī
    0.07
    线ä¸Ĭ线ä¸ĭ
    0.07
    è°©
    0.07
    Activations Density 0.794%

    No Known Activations