© 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. 13949
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by common words

    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
    以åıĬ
    -0.20
    /or
    -0.19
    åħ¶éĹ´
    -0.17
    轨
    -0.17
    èĢĮè¿Ļ
    -0.17
    åħ¶ä¸ŃåĮħæĭ¬
    -0.17
    并äºİ
    -0.17
    ç¯ĵ
    -0.17
    äºİæĺ¯æĪij
    -0.16
    aje
    -0.16
    POSITIVE LOGITS
     porém
    0.18
    aco
    0.17
    oco
    0.17
     заÑĢегиÑģÑĤ
    0.17
    astes
    0.17
    raction
    0.17
    äºĮåŃĹ
    0.17
    è´¢
    0.16
    -Language
    0.16
    PMC
    0.16
    Activations Density 0.220%

    No Known Activations