© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12467
    Prev
    Next
    INDEX
    Explanations

    v. followed by numbers or punctuation

    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
    pecified
    -0.19
    urer
    -0.17
    便äºİ
    -0.17
    shal
    -0.16
    ök
    -0.16
    /il
    -0.16
    quires
    -0.16
    ¤í
    -0.16
    appers
    -0.15
    ibling
    -0.15
    POSITIVE LOGITS
    acious
    0.20
    ical
    0.20
    icing
    0.19
    oodoo
    0.19
    åŃIJéĩĮ
    0.19
    eing
    0.18
    ooo
    0.18
    ious
    0.17
    ices
    0.17
    erson
    0.17
    Activations Density 0.102%

    No Known Activations