© 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. 11450
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çģŃ
    -0.20
    æĿ¼
    -0.20
    两个人
    -0.19
    åIJĪä½ľåħ³ç³»
    -0.18
    ä¸ŃåĽ½çĶµä¿¡
    -0.18
    è°³
    -0.18
    [section
    -0.18
    åĭ
    -0.18
    adden
    -0.18
    /release
    -0.18
    POSITIVE LOGITS
    åij³
    0.18
    iest
    0.18
    线索
    0.18
    çĹĽ
    0.17
    igator
    0.17
    éĩį
    0.17
     grav
    0.17
     Caucus
    0.17
     Castillo
    0.17
    grav
    0.17
    Activations Density 0.000%

    No Known Activations