© 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. 10759
    Prev
    Next
    INDEX
    Explanations

    listening to

    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
    绡
    -0.22
    [href
    -0.22
     Ñģобой
    -0.20
    antar
    -0.19
    _gui
    -0.19
    åĨµ
    -0.19
    awe
    -0.18
    gent
    -0.18
    _TP
    -0.17
    æıĨ
    -0.17
    POSITIVE LOGITS
    åĢ¾åIJ¬
    0.35
    èĢ³æľµ
    0.33
    èģĨ
    0.31
     ears
    0.30
    èģĨåIJ¬
    0.29
    ä¸ĢåIJ¬
    0.29
    ðŁijĤ
    0.29
     listens
    0.27
    åIJ¬åıĸ
    0.27
    åIJ¬çĿĢ
    0.27
    Activations Density 0.029%

    No Known Activations