© 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. 12437
    Prev
    Next
    INDEX
    Explanations

    debate

    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
    orate
    -0.19
    个交æĺĵ
    -0.18
    ollection
    -0.17
    !=(
    -0.17
    åıijå±ķåīįæĻ¯
    -0.17
    åįļçī©
    -0.17
    çĤ¬
    -0.17
    åıijå±ķæ½ľåĬĽ
    -0.16
    _except
    -0.16
    èĤ¡ä¸ľå¤§ä¼ļ
    -0.16
    POSITIVE LOGITS
    åľ¨äºİ
    0.18
    ä¸ŃæľĢ
    0.17
    èĤĭ
    0.17
    antium
    0.17
    uel
    0.17
    èĮķ
    0.17
    yll
    0.17
    izia
    0.17
    glas
    0.16
    åķ·
    0.16
    Activations Density 0.017%

    No Known Activations