© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16104
    Prev
    Next
    INDEX
    Explanations

    types of divisions or sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    /MIT
    -0.24
    ä¸įå½±åĵį
    -0.23
    åŃļ
    -0.21
    Spo
    -0.20
    äºĨäºĽ
    -0.19
    åħij
    -0.19
    (span
    -0.18
     dummy
    -0.18
    >[]
    -0.18
    éĽĨåĽ¢èĤ¡ä»½
    -0.18
    POSITIVE LOGITS
    è¯ħ
    0.26
    ä¸ĵéŨ
    0.21
    ä¸ĵé¢ĺ
    0.20
    UINT
    0.18
    ç¾°
    0.18
     warfare
    0.18
    è¿ĻåĿĹ
    0.18
    .Handler
    0.18
    åĪĽå»ºå·¥ä½ľ
    0.18
    æ¯Ľ
    0.18
    Activations Density 0.242%

    No Known Activations