© 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. 30937
    Prev
    Next
    INDEX
    Explanations

    medical conditions and their effects

    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
    iben
    -0.10
    è°¦
    -0.09
    oren
    -0.09
    ete
    -0.09
    çł´
    -0.09
    Dup
    -0.08
    æĹı
    -0.08
    .US
    -0.08
     US
    -0.08
    aju
    -0.08
    POSITIVE LOGITS
    åŃķèĤ²
    0.12
     tard
    0.10
    óng
    0.10
    åľ£è¯ŀ
    0.10
    åŀĤ
    0.09
    cock
    0.09
    EXIST
    0.09
    å²ĺ
    0.09
    _Register
    0.09
    ç²¾ç¥ŀ
    0.09
    Activations Density 0.152%

    No Known Activations