© 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. 11626
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    çŃĴ
    -0.20
    orra
    -0.19
     dong
    -0.18
    çĿĢæīĭ
    -0.18
    è¯ķéªĮåĮº
    -0.18
     yapılan
    -0.17
    ãĤĭãĤĤãģ®
    -0.17
    åľ°å¸¦
    -0.17
    娥
    -0.17
     Concord
    -0.16
    POSITIVE LOGITS
    ä¸İæѤ
    0.24
    ç¨Ķ
    0.21
    rens
    0.21
    blink
    0.19
    PBS
    0.19
    issy
    0.19
    _TOUCH
    0.19
    æºŁ
    0.19
    渴
    0.18
    åĢŁæѤ
    0.18
    Activations Density 0.704%

    No Known Activations