© 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. 15521
    Prev
    Next
    INDEX
    Explanations

    activity, rim, axis, scans

    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
     L
    -0.17
     S
    -0.17
     J
    -0.17
     D
    -0.16
     G
    -0.16
     M
    -0.16
     St
    -0.15
     F
    -0.15
     W
    -0.15
     da
    -0.15
    POSITIVE LOGITS
    $fdata
    0.17
    LIBINT
    0.16
    以ä¸ĭç®Ģ称
    0.15
     BCHP
    0.15
    ERRU
    0.15
    наÑĨионалÑĮн
    0.15
    индивид
    0.15
    $LANG
    0.14
    mPid
    0.14
    VMLINUX
    0.14
    Activations Density 18.175%

    No Known Activations