© 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. 10934
    Prev
    Next
    INDEX
    Explanations

    decide whether or on

    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
    /to
    -0.21
    age
    -0.18
    agus
    -0.18
    .cg
    -0.18
     mary
    -0.17
    津贴
    -0.17
    åķĨæĬ¥
    -0.16
     roma
    -0.16
    istani
    -0.16
    /from
    -0.16
    POSITIVE LOGITS
     rằng
    0.23
    ä¹İ
    0.19
    uil
    0.19
     lá»įc
    0.17
    /cal
    0.17
    ä¸į让
    0.16
    èĥľè´Ł
    0.16
     lá»±a
    0.16
    ments
    0.15
    ILED
    0.15
    Activations Density 0.037%

    No Known Activations