© 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. 15244
    Prev
    Next
    INDEX
    Explanations

    tractor

    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
     dÃłng
    -0.18
    cape
    -0.17
    igte
    -0.17
    ระà¸ļ
    -0.17
    cookie
    -0.17
    eenth
    -0.17
    xious
    -0.17
    ifica
    -0.15
    éķĬ
    -0.15
    ä¹ĭä½ľ
    -0.15
    POSITIVE LOGITS
    oup
    0.20
    èĢķ
    0.19
    eer
    0.19
    oon
    0.19
    eur
    0.18
    ±
    0.18
    ipl
    0.17
    è½°
    0.17
    èĢķåľ°
    0.17
    eurs
    0.16
    Activations Density 0.007%

    No Known Activations