© 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. 13294
    Prev
    Next
    INDEX
    Explanations

    game developers and publishers

    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
    飬
    -0.20
    iano
    -0.20
    箧
    -0.19
    èĬ±èįī
    -0.18
    èī²æ³½
    -0.18
    æĿ¡ä»¶ä¸ĭ
    -0.18
    书é¦Ļ
    -0.17
    zem
    -0.17
    arella
    -0.17
    icity
    -0.17
    POSITIVE LOGITS
    å±
    0.21
    -icons
    0.20
    åİŁåħĪ
    0.19
    è½®æµģ
    0.19
    éĩijæ²Ļ
    0.19
    locs
    0.19
    .getUserName
    0.18
    äºĨ解åĪ°
    0.18
    认åı¯
    0.18
    æĢ»éĥ¨
    0.18
    Activations Density 0.006%

    No Known Activations