© 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. 13438
    Prev
    Next
    INDEX
    Explanations

    words followed by initials or numbers

    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
    gro
    -0.21
    PO
    -0.20
    ç¾İæľ¯
    -0.20
    示
    -0.20
    æĪij们认为
    -0.19
     rein
    -0.18
    Č
    -0.18
    gia
    -0.18
    uct
    -0.17
    eli
    -0.17
    POSITIVE LOGITS
    çĪĶ
    0.23
    é«ĺæĺĤ
    0.21
    åħ¨æĸ°
    0.19
    æ¼ĭ
    0.19
    æįIJåĬ©
    0.19
    æ¥Ĵ
    0.19
    å¸Ńæī§è¡Į
    0.18
    åĴ¡
    0.18
    é¢Ħè§ģ
    0.18
    è§Ń
    0.18
    Activations Density 0.033%

    No Known Activations