© 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. 19255
    Prev
    Next
    INDEX
    Explanations

    retinoic acid, retinoid

    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
    æ¯ĶåĪĨ
    -0.09
    .broadcast
    -0.08
    оÑĢÑĤ
    -0.08
    gué
    -0.08
    oyo
    -0.08
    ãĥ¡ãĥ³ãĥIJãĥ¼
    -0.08
    sumer
    -0.08
     вÑģÑĤÑĢеÑĩа
    -0.08
    ä¸Ĭ游
    -0.08
     nắng
    -0.08
    POSITIVE LOGITS
    åĻ¬
    0.10
    åĶĨ
    0.09
    é£ĺ
    0.09
    Swap
    0.08
    urge
    0.08
    å¬Ĺ
    0.08
    _sur
    0.08
    horn
    0.08
    棱
    0.08
    æĥ«
    0.08
    Activations Density 0.074%

    No Known Activations