© 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. 11377
    Prev
    Next
    INDEX
    Explanations

    cut with butter

    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
    åĪ°æľŁ
    -0.20
    åĩºåĵģ
    -0.20
    unda
    -0.20
    èµħ
    -0.20
    åıijçĶŁåľ¨
    -0.19
    åīį沿
    -0.19
    èĪªè¡Į
    -0.19
    [][
    -0.19
    驶
    -0.19
    æ³ĩ
    -0.19
    POSITIVE LOGITS
    èIJ¥éĢł
    0.21
     ÙĪاÙĦÙģ
    0.20
    绺
    0.20
     biscuits
    0.19
    èĵij
    0.19
     dá»±ng
    0.19
    ä»İæľª
    0.18
    gether
    0.18
    quist
    0.18
     alternate
    0.18
    Activations Density 0.011%

    No Known Activations