© 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. 13524
    Prev
    Next
    INDEX
    Explanations

    background information

    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
    burgh
    -0.19
    /qu
    -0.18
    istic
    -0.18
    egment
    -0.17
    åıĮèĦļ
    -0.16
    /her
    -0.16
    *angstrom
    -0.16
    ifiable
    -0.16
    èĪªçº¿
    -0.16
    andro
    -0.16
    POSITIVE LOGITS
    sWith
    0.23
    人士
    0.19
    /background
    0.18
    åIJĦå¼Ĥ
    0.17
    oring
    0.17
    less
    0.17
    ed
    0.17
    èĮ¬
    0.17
    zee
    0.16
    edly
    0.16
    Activations Density 0.039%

    No Known Activations