© 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. 22534
    Prev
    Next
    INDEX
    Explanations

    adjacent followed by noun

    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
    fully
    -0.10
    hardt
    -0.09
    ishing
    -0.09
    èĪ«
    -0.09
    cher
    -0.09
    çļ¿
    -0.09
    ations
    -0.08
    borne
    -0.08
    tram
    -0.08
    à¤ŀ
    -0.08
    POSITIVE LOGITS
    cy
    0.10
    ä¸įè¿ľ
    0.10
    èĢĮåıĪ
    0.10
    姻
    0.09
    emen
    0.09
    ively
    0.09
    èĬ±æľµ
    0.09
    WISE
    0.09
    elig
    0.09
    åĩłå®¶
    0.08
    Activations Density 0.022%

    No Known Activations