© 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. 26808
    Prev
    Next
    INDEX
    Explanations

    medical conditions and syndromes

    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
    çĺ¾
    -0.11
    å¨ģèĥģ
    -0.09
    æĮ½
    -0.09
    obot
    -0.09
    obil
    -0.08
    请æķĻ
    -0.08
    agi
    -0.08
    loat
    -0.08
    .FILL
    -0.08
    ellen
    -0.08
    POSITIVE LOGITS
    çĹĩ
    0.10
    åIJİå¤ĩ
    0.09
    毡
    0.09
    çĹª
    0.09
    ее
    0.09
    vore
    0.09
    wis
    0.09
    çŃĭ
    0.08
    éĺ¶å±Ĥ
    0.08
    纤
    0.08
    Activations Density 0.029%

    No Known Activations