© 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. 14413
    Prev
    Next
    INDEX
    Explanations

    alleged actions or claims

    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
    eller
    -0.18
    æķ´æ´ģ
    -0.17
    niest
    -0.17
    æł·çļĦ
    -0.16
    obl
    -0.16
    plr
    -0.16
    ugal
    -0.16
    åĽŀåij³
    -0.16
    erals
    -0.15
    ulan
    -0.15
    POSITIVE LOGITS
    ged
    0.23
    oric
    0.18
    ging
    0.18
    ìĤ¬íķŃ
    0.17
    andro
    0.17
    ted
    0.16
    reate
    0.16
    /assert
    0.16
    phas
    0.16
    aire
    0.16
    Activations Density 0.009%

    No Known Activations