© 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. 16371
    Prev
    Next
    INDEX
    Explanations

    calibers or numbers

    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
    bron
    -0.20
    å®ŀå®ŀåľ¨åľ¨
    -0.20
    åĽ½å®ī
    -0.20
    _IOCTL
    -0.19
     tal
    -0.19
    åıĺçİ°
    -0.19
    é£İæ°Ķ
    -0.18
    æĨĶ
    -0.18
    çĽĺ
    -0.18
    åĴ¸
    -0.18
    POSITIVE LOGITS
     BITS
    0.19
    .nr
    0.18
     Reload
    0.18
    绲
    0.18
    aviest
    0.18
    suit
    0.17
    _foreign
    0.17
    rin
    0.17
    .pin
    0.17
     caliber
    0.17
    Activations Density 0.005%

    No Known Activations