© 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. 12734
    Prev
    Next
    INDEX
    Explanations

    lake followed by a place name

    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
    uted
    -0.17
    »
    -0.17
    sed
    -0.16
    ©
    -0.16
    {/
    -0.16
    laughter
    -0.16
    tees
    -0.15
    èī¯å¿ĥ
    -0.15
    sdk
    -0.15
    çĤĶ
    -0.15
    POSITIVE LOGITS
    hores
    0.30
    çķĶ
    0.22
    çĶŁäº§æĢ»åĢ¼
    0.18
    yards
    0.17
     Tahoe
    0.17
    front
    0.17
    let
    0.15
    eing
    0.15
    人士
    0.15
     Superior
    0.15
    Activations Density 0.018%

    No Known Activations