© 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. 14544
    Prev
    Next
    INDEX
    Explanations

    script without

    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
     kitty
    -0.21
    è·¯åı£
    -0.20
    çļĦæľĭåıĭ
    -0.19
    ä»»æĢ§
    -0.19
    _DF
    -0.19
    éģģ
    -0.18
    天ä¸ĭ
    -0.17
    nesc
    -0.17
    alle
    -0.17
    åĢĻ
    -0.17
    POSITIVE LOGITS
    à¹Ģà¸ķ
    0.23
    ä¸įä»ħä»ħ
    0.22
    ä¸įä»ħä»ħæĺ¯
    0.21
     phấn
    0.20
    ä¸įæŃ¢
    0.19
    ahl
    0.19
    ad
    0.18
    adan
    0.18
    åħ¶å®ĥ
    0.18
    赪
    0.18
    Activations Density 0.645%

    No Known Activations