© 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. 11969
    Prev
    Next
    INDEX
    Explanations

    glassware

    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
    usable
    -0.16
    nung
    -0.16
    alse
    -0.15
    æİĮæı¡äºĨ
    -0.15
    <?,
    -0.14
    qua
    -0.14
    컬
    -0.14
    åħ¥å¸Ĥ
    -0.14
    executable
    -0.14
     Skill
    -0.14
    POSITIVE LOGITS
    maker
    0.23
    åŃIJéĩĮ
    0.20
    mates
    0.20
    matic
    0.19
    (es
    0.19
    making
    0.19
    mate
    0.18
    cribe
    0.18
    gow
    0.18
    rpc
    0.18
    Activations Density 0.014%

    No Known Activations