© 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. 11139
    Prev
    Next
    INDEX
    Explanations

    other kinds of

    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
    ä¸İåIJ¦
    -0.24
     Ow
    -0.20
    izzy
    -0.19
    äºĮåŃĹ
    -0.19
     itself
    -0.18
    æѧ
    -0.18
     everybody
    -0.18
    aland
    -0.18
     centerpiece
    -0.18
    ä¸ĭä¸Ģ代
    -0.18
    POSITIVE LOGITS
    诸å¦Ĥ
    0.28
    -than
    0.24
     niż
    0.23
    _THAN
    0.22
    Than
    0.21
    sha
    0.21
     ÐIJлекÑģан
    0.20
    åĪĻæĺ¯
    0.20
     ÐĶмиÑĤÑĢ
    0.20
    world
    0.19
    Activations Density 0.090%

    No Known Activations