© 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. 11830
    Prev
    Next
    INDEX
    Explanations

    crisis

    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
    sWith
    -0.26
    ees
    -0.20
    orate
    -0.19
    eced
    -0.18
    ee
    -0.17
    sert
    -0.17
    ritch
    -0.17
    æĸ°ä¸ĸ纪
    -0.17
    /disable
    -0.17
    eah
    -0.16
    POSITIVE LOGITS
    rd
    0.23
    éĩįéĩį
    0.20
     unnamed
    0.17
    ly
    0.17
    wal
    0.16
    SED
    0.16
    elves
    0.16
    vale
    0.16
    unning
    0.16
    dem
    0.16
    Activations Density 0.008%

    No Known Activations