© 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. 11026
    Prev
    Next
    INDEX
    Explanations

    reporting verbs after names

    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
    è¾±
    -0.23
    æģ¤
    -0.20
     poster
    -0.19
    çĥ«
    -0.18
    åIJİåĨį
    -0.18
    åĹ
    -0.18
    poster
    -0.17
    침
    -0.17
    elve
    -0.17
    ä¸įåı¯éģ¿åħį
    -0.17
    POSITIVE LOGITS
    åĪĨ管
    0.22
    ä»ĭç»į说
    0.22
    mens
    0.21
    ä»ĸ表示
    0.20
    åı¹æģ¯
    0.20
    åľ¨æİ¥åıĹ
    0.20
    å½ĵåľ°æŶéĹ´
    0.19
    æĹ¥åīį
    0.19
    颤
    0.19
    еÑĨ
    0.19
    Activations Density 0.030%

    No Known Activations