© 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. 56872
    Prev
    Next
    INDEX
    Explanations

    from the

    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
    ipt
    -0.09
    ä½łèĩªå·±
    -0.09
    etur
    -0.08
    ä¸ĢéĹª
    -0.08
     Ñģебе
    -0.08
    éĥĩ
    -0.08
    å·©
    -0.08
    kir
    -0.08
    å·´æĸ¯
    -0.08
    sworth
    -0.08
    POSITIVE LOGITS
    upe
    0.09
    ÙĦÙĪ
    0.09
     goose
    0.09
    -Speed
    0.08
    åŃ½
    0.08
    obox
    0.08
     envi
    0.08
    大åıij
    0.08
    IME
    0.08
    ItemAt
    0.08
    Activations Density 0.006%

    No Known Activations