© 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. 15766
    Prev
    Next
    INDEX
    Explanations

    kids

    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
    /or
    -0.19
    kommen
    -0.18
    alie
    -0.18
    eker
    -0.17
    /if
    -0.17
    _KEYBOARD
    -0.17
    umba
    -0.16
    æĻ°
    -0.16
    ableView
    -0.16
    vÃŃ
    -0.16
    POSITIVE LOGITS
    nap
    0.28
    ifying
    0.23
    ified
    0.20
    åĦ¿
    0.19
    åħĴ
    0.19
    ult
    0.19
    ney
    0.18
    们çļĦ
    0.18
    们éĥ½
    0.18
    窿
    0.17
    Activations Density 0.012%

    No Known Activations