© 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. 15452
    Prev
    Next
    INDEX
    Explanations

    physical descriptions and traits

    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
    æ¯Ķè¾ĥç®Ģåįķ
    -0.21
    è¿Ļçīĩ
    -0.21
    ICODE
    -0.20
    女çİĭ
    -0.20
    _userdata
    -0.20
    å¾Īç®Ģåįķ
    -0.20
    èĹIJ
    -0.19
    çŀĭ
    -0.18
    èĮ«èĮ«
    -0.18
     оÑģнован
    -0.18
    POSITIVE LOGITS
    ä¸ij
    0.22
    滨
    0.19
    åıijåĩº
    0.19
     Persian
    0.19
     bulb
    0.18
    ä¸ĵèģĮ
    0.18
    æĴ
    0.18
     intellectual
    0.18
    çī¹å¾ģ
    0.18
     fatt
    0.17
    Activations Density 0.026%

    No Known Activations