© 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. 18865
    Prev
    Next
    INDEX
    Explanations

    expression of specific entities

    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
    actic
    -0.10
    大家ä¸Ģèµ·
    -0.10
    à¸ķา
    -0.09
    æĪij们ä¸Ģèµ·
    -0.09
    up
    -0.09
    ä½ķå¤Ħ
    -0.08
    ously
    -0.08
    jer
    -0.08
    ä¸Ģèµ·
    -0.08
    ye
    -0.08
    POSITIVE LOGITS
    ively
    0.17
    SION
    0.10
    ional
    0.09
    iveness
    0.09
    ITE
    0.09
    ¹
    0.09
    iments
    0.09
    ç¨İåĬ¡å±Ģ
    0.09
    ible
    0.09
    ions
    0.09
    Activations Density 0.120%

    No Known Activations