© 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. 58307
    Prev
    Next
    INDEX
    Explanations

    midfielder or midfield

    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
    neau
    -0.09
    åī¯æĢ»
    -0.09
    ä¸ŃæĸŃ
    -0.09
    ãģĮãĤī
    -0.09
    iance
    -0.09
    ment
    -0.09
    ubo
    -0.08
    éĿ¢èī²
    -0.08
    çĺĢ
    -0.08
    athan
    -0.08
    POSITIVE LOGITS
    entifier
    0.11
    ä¿Ŀåħ»
    0.09
    è¾ĪåŃIJ
    0.09
    iggins
    0.09
    çĻ¾ç§ij
    0.09
    -most
    0.09
    unya
    0.09
    èī²è°ĥ
    0.09
    /Gate
    0.09
    tures
    0.08
    Activations Density 0.021%

    No Known Activations