© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15346
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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
    踵
    -0.20
    hta
    -0.19
    -align
    -0.18
    æŁģ
    -0.18
    _DT
    -0.17
    æŶåħī
    -0.17
    å¤ĸè§Ĥ
    -0.17
    ä¸ĵ项è¡ĮåĬ¨
    -0.17
    _ALIGN
    -0.17
    èķĻ
    -0.17
    POSITIVE LOGITS
    åºŁ
    0.22
    æ¯Ľ
    0.21
    icult
    0.21
     Fors
    0.20
    Queryable
    0.19
    å°Ķæĸ¯
    0.19
    ode
    0.19
    è´¥
    0.18
     Wend
    0.18
    åįĹéĢļ
    0.18
    Activations Density 0.002%

    No Known Activations