© 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. 16530
    Prev
    Next
    INDEX
    Explanations

    musicians and bands

    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
    sam
    -0.20
    é«ĺä¸ī
    -0.19
     Zimmerman
    -0.19
    å¤±æľĽ
    -0.19
    åīįåįģ
    -0.19
     Dial
    -0.19
    ç±į
    -0.18
    ç¥ŀåĻ¨
    -0.18
    ampions
    -0.18
    æĺķ
    -0.18
    POSITIVE LOGITS
    quir
    0.19
    çŁ³æ¦´
    0.19
    §
    0.19
    lines
    0.18
    UCH
    0.18
    구
    0.18
    çĭĴ
    0.18
    amo
    0.18
    éĿ¡
    0.18
    èľ¥
    0.18
    Activations Density 0.016%

    No Known Activations