© 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. 14315
    Prev
    Next
    INDEX
    Explanations

    character sequences

    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
    lige
    -0.20
    ctor
    -0.20
    lia
    -0.19
    两ç§į
    -0.19
    nder
    -0.19
     TCL
    -0.17
    ing
    -0.16
     Vim
    -0.16
    assing
    -0.16
     acid
    -0.16
    POSITIVE LOGITS
    èµ·æĿ¥äºĨ
    0.20
    å¥Ī
    0.20
    淹没
    0.19
    æ³»
    0.19
    æĿµ
    0.19
    opal
    0.19
    çĸŁ
    0.18
    ISH
    0.18
    椴
    0.18
    à¹Ĩ
    0.18
    Activations Density 0.057%

    No Known Activations