© 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. 10958
    Prev
    Next
    INDEX
    Explanations

    back and forth movement

    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
    æĻ°
    -0.23
    ider
    -0.22
    åŁĴ
    -0.21
    ÑĢад
    -0.18
    ekt
    -0.18
    apus
    -0.17
    ä¸ĭä¸Ģ代
    -0.17
    iks
    -0.17
    éªIJ
    -0.17
    éºŁ
    -0.17
    POSITIVE LOGITS
    ç©¿æ¢Ń
    0.30
    èĩªå¦Ĥ
    0.29
     between
    0.29
     междÑĥ
    0.26
    åıįå¤į
    0.25
    å¾Ģè¿Ķ
    0.25
    è¿Ľåĩº
    0.24
    between
    0.23
    é¢ijç¹ģ
    0.23
    åĩłæ¬¡
    0.23
    Activations Density 0.049%

    No Known Activations