© 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. 11759
    Prev
    Next
    INDEX
    Explanations

    take you to

    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
    å¾µ
    -0.20
    atham
    -0.20
    aris
    -0.19
    椽
    -0.19
    PropertyParams
    -0.18
    (equal
    -0.18
    HeaderCode
    -0.18
     بØŃÙĬ
    -0.18
    isko
    -0.18
    .Bot
    -0.18
    POSITIVE LOGITS
    å¼¹
    0.25
    åĪ°
    0.24
    è¿Ľåħ¥
    0.24
    éĵ¾æİ¥
    0.23
    缮çļĦåľ°
    0.21
    éĢ²åħ¥
    0.21
     ÑģÑĢазÑĥ
    0.20
    åĪ°è¿ĻéĩĮ
    0.20
    ä¸ĭä¸ĢæŃ¥
    0.20
    åĪ°æľĢåIJİ
    0.19
    Activations Density 0.071%

    No Known Activations