© 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. 11019
    Prev
    Next
    INDEX
    Explanations

    Min

    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
    ness
    -0.20
    ngine
    -0.20
    tlement
    -0.18
    onical
    -0.17
    NESS
    -0.17
    ams
    -0.17
    eenth
    -0.16
    ronym
    -0.16
    auty
    -0.15
    橹
    -0.15
    POSITIVE LOGITS
    -être
    0.24
    ç²¹
    0.19
    elman
    0.18
     дело
    0.18
    -UA
    0.18
    èĩ¾
    0.17
    IONS
    0.16
    ice
    0.16
    ally
    0.16
     Niet
    0.16
    Activations Density 0.024%

    No Known Activations