© 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. 18455
    Prev
    Next
    INDEX
    Explanations

    vitamin deficiency signs

    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
    é¼¾
    -0.10
    IEW
    -0.10
    çĶµéĩı
    -0.10
    è°¦
    -0.09
    访
    -0.09
    家纺
    -0.09
    çŁ¥å·±
    -0.09
    azy
    -0.09
    éĢĢç¨İ
    -0.09
    TED
    -0.09
    POSITIVE LOGITS
    æ¼ı
    0.10
    è¡¥åħħ
    0.09
     Guerr
    0.09
    åݨå¸Ī
    0.09
    åĤ¨å¤ĩ
    0.09
    çļĦç²¾ç¥ŀ
    0.09
    parity
    0.08
    åĪ»èĭ¦
    0.08
    witter
    0.08
    adle
    0.08
    Activations Density 0.194%

    No Known Activations