© 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. 13662
    Prev
    Next
    INDEX
    Explanations

    basketball defender or man

    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
    forme
    -0.21
     Affero
    -0.19
    èĥĮæĻ¯
    -0.19
    龸
    -0.18
    æ°ijèIJ¥
    -0.18
    prising
    -0.18
    çıįæĥľ
    -0.18
    çģ°èī²
    -0.18
    ENCE
    -0.18
    åĿĬ
    -0.17
    POSITIVE LOGITS
    åħ³ç³»
    0.24
     link
    0.20
     relationships
    0.19
    nost
    0.19
    ìłĪ
    0.19
     situations
    0.18
     relations
    0.18
    gable
    0.18
    Bindable
    0.18
    ely
    0.17
    Activations Density 0.002%

    No Known Activations