© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15146
    Prev
    Next
    INDEX
    Explanations

    premolar teeth and molars

    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
     Burnett
    -0.20
    inski
    -0.20
    ivi
    -0.20
    rita
    -0.20
    Bush
    -0.19
    çĿ¥
    -0.19
     Wolves
    -0.18
    _Element
    -0.18
    çĹŀ
    -0.18
    -motion
    -0.18
    POSITIVE LOGITS
    è¿ģ
    0.21
    ç«ŀ
    0.20
    è¿ij
    0.19
    çĶ¨äºİ
    0.19
    æĿ¥è¯´
    0.19
    -fly
    0.18
    ç¼Ķ
    0.18
    æ¯ıä¸Ģ次
    0.18
    å±Ĥ次
    0.18
    æī¿åĬŀ
    0.18
    Activations Density 0.001%

    No Known Activations