© 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. 17575
    Prev
    Next
    INDEX
    Explanations

    College followed by department

    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
    ../../../
    -0.11
    ners
    -0.10
    çĮ·
    -0.09
    teenth
    -0.09
    å°±åĮ»
    -0.09
    æ²³æµģåŁŁ
    -0.09
    elle
    -0.09
    ãģıãĤĮ
    -0.09
    cip
    -0.08
    ä¹ĭ家
    -0.08
    POSITIVE LOGITS
    mates
    0.10
    гоÑĢ
    0.10
    为空
    0.09
    ords
    0.09
    ×ķת
    0.09
    ibrary
    0.09
    çļĭ
    0.09
    mate
    0.09
    ence
    0.09
    ording
    0.09
    Activations Density 0.028%

    No Known Activations