© 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. 13775
    Prev
    Next
    INDEX
    Explanations

    description of plants

    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
    幸好
    -0.22
    -slot
    -0.21
    èĬ±æł·
    -0.21
    shape
    -0.21
    lap
    -0.20
    轩
    -0.19
    åĸĿäºĨ
    -0.19
    åĪ¹è½¦
    -0.19
    éĴ¥åĮĻ
    -0.18
    ç¤ģ
    -0.18
    POSITIVE LOGITS
    _URI
    0.22
    éĥ¢
    0.22
     ÑĢаÑģÑħод
    0.19
    евиÑĩ
    0.19
    纨
    0.19
    agus
    0.19
    éĢĭ
    0.19
     Fé
    0.18
    efe
    0.18
    两岸
    0.18
    Activations Density 0.021%

    No Known Activations