© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14935
    Prev
    Next
    INDEX
    Explanations

    band names, artist names, song names

    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
    .nom
    -0.23
    nom
    -0.22
    akedown
    -0.19
     NOM
    -0.19
    纫
    -0.19
    afone
    -0.18
    ance
    -0.18
    Mutation
    -0.18
     Nom
    -0.17
    女æĺŁ
    -0.17
    POSITIVE LOGITS
    å¡Ķ
    0.21
    éľŀ
    0.21
    ä¸Ģ举
    0.21
    åħ¬é¡·
    0.20
    éĤ¸
    0.20
    夺
    0.20
    éĺģ
    0.19
     McConnell
    0.18
    åı¸é©¬
    0.18
    å¹´æĬ¥
    0.18
    Activations Density 0.002%

    No Known Activations