© 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. 13507
    Prev
    Next
    INDEX
    Explanations

    subject class

    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
    çĶŁåŃĺ
    -0.19
    ogi
    -0.18
    åIJįåŃĹ
    -0.17
    fts
    -0.17
    isman
    -0.17
     stir
    -0.17
    ël
    -0.17
     ade
    -0.17
    å¤ļå°ij
    -0.17
    ÄĽ
    -0.16
    POSITIVE LOGITS
    ç»ĨåĪĨ
    0.20
    yat
    0.20
    oise
    0.19
    ythe
    0.19
    __),
    0.18
    عÙĤ
    0.18
    rays
    0.18
    payer
    0.18
    alink
    0.18
    romise
    0.17
    Activations Density 0.008%

    No Known Activations