© 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. 11426
    Prev
    Next
    INDEX
    Explanations

    skin or skinny descriptions

    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
    ncia
    -0.17
    -www
    -0.17
    uality
    -0.17
    é¬ĵ
    -0.16
    nement
    -0.16
    ä¼ī
    -0.16
    eker
    -0.16
    .edges
    -0.16
    aca
    -0.16
    ments
    -0.16
    POSITIVE LOGITS
    paces
    0.17
    åľ°å¸¦
    0.16
    osate
    0.15
    cies
    0.15
    é¹ħ
    0.15
     narz
    0.15
    ä¸ŃåĽ½åĽ½éĻħ
    0.15
    å¸Ļ
    0.15
    adic
    0.15
     воÑĤ
    0.15
    Activations Density 0.002%

    No Known Activations