© 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. 10999
    Prev
    Next
    INDEX
    Explanations

    Copyright and license information

    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
    ImageRelation
    -0.23
    /photos
    -0.21
    CloseOperation
    -0.21
    åıĭ们
    -0.20
    sPid
    -0.20
    FilterWhere
    -0.20
    mPid
    -0.19
    CallableWrapper
    -0.18
    createForm
    -0.18
    oyer
    -0.18
    POSITIVE LOGITS
    fx
    0.20
    k
    0.20
    ç½²
    0.19
    Transparent
    0.18
    ç«Ļ
    0.18
    å¸Į
    0.18
    æī§æ³ķ
    0.18
    åŃĹ
    0.18
    ruise
    0.18
    oto
    0.18
    Activations Density 0.358%

    No Known Activations