© 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. 15871
    Prev
    Next
    INDEX
    Explanations

    distances or measurements

    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
    ktop
    -0.23
    å®īåħ¨æĦŁ
    -0.22
    åĴ½åĸī
    -0.20
    头ä¸Ĭ
    -0.20
    umat
    -0.19
    æ´Ħ
    -0.18
    logg
    -0.18
    éľ°
    -0.18
    头éĥ¨
    -0.18
     Champ
    -0.18
    POSITIVE LOGITS
    (distance
    0.22
     distance
    0.21
    -distance
    0.21
    distance
    0.20
    è·Ŀ离
    0.20
    åĽ¢ä½ĵ
    0.20
    .distance
    0.20
    çľĭåĩº
    0.20
    Distance
    0.20
    olen
    0.20
    Activations Density 0.008%

    No Known Activations