© 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. 15808
    Prev
    Next
    INDEX
    Explanations

    reptiles and lizards

    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
    æĹĥ
    -0.18
    å¹³åİŁ
    -0.18
    è£
    -0.18
    次æķ°
    -0.17
    omm
    -0.17
    é¡¿
    -0.17
    驺
    -0.17
    éĵĥ
    -0.17
    æ°´è´¨
    -0.17
    髦
    -0.17
    POSITIVE LOGITS
    èľ´
    0.28
    èľ¥
    0.22
     Clint
    0.17
    ilian
    0.17
    (hex
    0.16
    lets
    0.16
    blink
    0.16
     parch
    0.16
    èĽĭ
    0.16
    zman
    0.16
    Activations Density 0.005%

    No Known Activations