© 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. 14114
    Prev
    Next
    INDEX
    Explanations

    calibration and related processes

    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
    burn
    -0.18
    apel
    -0.17
    .ssl
    -0.17
    acher
    -0.17
    letic
    -0.17
    ç»°
    -0.17
    itive
    -0.17
    ritch
    -0.17
    AuthProvider
    -0.16
    åĮı
    -0.16
    POSITIVE LOGITS
    失误
    0.18
    reuse
    0.18
    łí
    0.17
    rek
    0.17
    è¿ĩçļĦ
    0.17
    æİ¥çĿĢ
    0.17
    ä¸İåıijå±ķ
    0.17
    UNG
    0.17
    unning
    0.17
    大å¸Ī
    0.17
    Activations Density 0.017%

    No Known Activations