© 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. 15130
    Prev
    Next
    INDEX
    Explanations

    knock out or down

    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
    gtest
    -0.19
    -même
    -0.19
    ality
    -0.18
    irty
    -0.18
    Į
    -0.17
    zug
    -0.16
    ãĥ£
    -0.16
    ially
    -0.16
    keit
    -0.15
     Santo
    -0.15
    POSITIVE LOGITS
    edList
    0.23
    outs
    0.20
    ingly
    0.20
    edException
    0.19
    down
    0.19
    aroo
    0.19
    ers
    0.18
    ä¸ŃåĽ½ä¼łç»Ł
    0.18
    loads
    0.17
    appa
    0.17
    Activations Density 0.006%

    No Known Activations