© 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. 13555
    Prev
    Next
    INDEX
    Explanations

    nanostructures (nanowires, nanotubes, nanocrystals, nanoparticles)

    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
    Stamp
    -0.20
     Conveyor
    -0.19
    åijĭ
    -0.19
    æ±²
    -0.19
    ers
    -0.18
    ÑĢÑıд
    -0.18
    ming
    -0.18
     Dexter
    -0.17
    æı£
    -0.17
    overs
    -0.17
    POSITIVE LOGITS
    ä¹ĭ家
    0.23
    åºĨ幸
    0.20
    认åı¯
    0.20
    å°ıäºĭ
    0.19
    ule
    0.19
    èĿī
    0.19
    èĤ¡
    0.18
     playable
    0.18
    æ±Ĺ
    0.18
    æŁĦ
    0.18
    Activations Density 0.002%

    No Known Activations