© 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. 15500
    Prev
    Next
    INDEX
    Explanations

    property of

    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
     bir
    -0.22
    åĥļ
    -0.22
    åįĴ
    -0.20
    觳
    -0.20
     tot
    -0.19
    bir
    -0.18
    åĥı个
    -0.18
    Wo
    -0.18
     Erotische
    -0.18
    isz
    -0.18
    POSITIVE LOGITS
    ä½ľèĢħæīĢæľī
    0.25
    åIJĪæ³ķæĿĥçĽĬ
    0.19
    年以ä¸Ĭ
    0.19
    è¿Ļ家åħ¬åı¸
    0.19
    çīĪæĿĥå½ĴåİŁ
    0.18
    Luck
    0.17
    åīľ
    0.17
    å¼ĢçĽĺ
    0.17
    丰ç¡ķ
    0.17
    mitt
    0.17
    Activations Density 0.006%

    No Known Activations