© 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. 14667
    Prev
    Next
    INDEX
    Explanations

    ПÑĢоÑĤеÑĤеÑđаÑĦе

    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
    pline
    -0.18
    çĦ¶
    -0.16
    çĶŁæĢķ
    -0.16
    åħļçļĦé¢Ĩ导
    -0.16
    /out
    -0.15
    astr
    -0.15
    inic
    -0.15
    anos
    -0.15
    ´
    -0.15
    izzo
    -0.15
    POSITIVE LOGITS
    sth
    0.19
    iants
    0.19
    iator
    0.18
    ination
    0.17
    äºĨ个
    0.17
    ely
    0.17
    tributes
    0.16
    гÑĢÑĥз
    0.16
    ned
    0.16
    leigh
    0.16
    Activations Density 0.018%

    No Known Activations