© 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. 13740
    Prev
    Next
    INDEX
    Explanations

    pinch or ching or inch

    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
    llen
    -0.18
    asca
    -0.17
    reck
    -0.17
    ศาส
    -0.17
    æ³ħ
    -0.17
    selection
    -0.16
    asmus
    -0.16
    perator
    -0.16
    ãģĦãģŁãĤī
    -0.16
    phas
    -0.16
    POSITIVE LOGITS
    ingly
    0.25
    ذا
    0.20
    è¦ģ害
    0.19
    sure
    0.19
    ermen
    0.19
    stick
    0.18
    imizer
    0.18
    outs
    0.18
    less
    0.17
    site
    0.17
    Activations Density 0.005%

    No Known Activations