© 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. 32104
    Prev
    Next
    INDEX
    Explanations

    luteinizing hormone

    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
    åį§
    -0.10
    bee
    -0.09
    moz
    -0.09
    çĪª
    -0.09
     lev
    -0.09
    OnError
    -0.09
    .choose
    -0.08
    erus
    -0.08
    åĨ¥
    -0.08
    sted
    -0.08
    POSITIVE LOGITS
    æļĤ
    0.10
    è¯Ħæ¯Ķ
    0.10
    æĹ·
    0.10
    ramid
    0.10
    æŁ¥çľĭåħ¨æĸĩ
    0.09
    åĸīåĴĻ
    0.09
    bundles
    0.09
     пÑĥ
    0.09
    åŀŃ
    0.09
    å¿ĥè¡Ģ
    0.09
    Activations Density 0.123%

    No Known Activations