© 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. 12157
    Prev
    Next
    INDEX
    Explanations

    contact numbers

    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
     Ashe
    -0.20
    æĪijåĽ½
    -0.19
    æĺ¯å¯¹
    -0.18
    æĪĸæĺ¯
    -0.18
    åħ¥
    -0.18
    oret
    -0.18
     Webster
    -0.18
    ione
    -0.18
    åĢį
    -0.18
    ideo
    -0.18
    POSITIVE LOGITS
    eday
    0.21
    atee
    0.20
    hound
    0.20
    çŃ¹èµĦ
    0.20
    æİĴè¡Į
    0.20
    менно
    0.19
    ðŁĺ©
    0.18
    æ¯Ķè¾ĥé«ĺ
    0.18
    ÑĢÑıд
    0.18
    濯
    0.18
    Activations Density 0.010%

    No Known Activations