© 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. 33286
    Prev
    Next
    INDEX
    Explanations

    pathways or ways to something

    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
    ened
    -0.12
    ×ķת
    -0.11
    nable
    -0.10
    iness
    -0.10
    -0.09
    prep
    -0.09
    ned
    -0.09
    uated
    -0.09
    scape
    -0.09
    åĮ»ç§ij大åѦ
    -0.09
    POSITIVE LOGITS
    们
    0.11
    ÑģÑı
    0.11
    们éĥ½
    0.09
    æľīæķĪæĢ§
    0.09
    å¿įåıĹ
    0.09
    aru
    0.09
    themes
    0.09
    ľ
    0.09
    ä¼Ļ
    0.08
    èĢģåħµ
    0.08
    Activations Density 0.013%

    No Known Activations