© 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. 13733
    Prev
    Next
    INDEX
    Explanations

    NY slip opinions

    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
    梯
    -0.20
    èĩ¾
    -0.20
    éĿĸ
    -0.19
    aise
    -0.19
    lia
    -0.18
     Spiral
    -0.18
    æ°´æµģ
    -0.18
    GRP
    -0.18
    .gf
    -0.18
    lest
    -0.17
    POSITIVE LOGITS
    ieri
    0.20
    ^^^^
    0.19
    anguage
    0.19
    åĹĵåŃIJ
    0.18
    æľ¬ç½ij
    0.18
     incom
    0.18
    èĤ¤èī²
    0.18
    ä¸įç»ı
    0.17
    -seat
    0.17
    寮
    0.17
    Activations Density 0.001%

    No Known Activations