© 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. 12497
    Prev
    Next
    INDEX
    Explanations

    carcinogens or carcinogenic

    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
    ãģĽãģĦ
    -0.20
    è¶Ĭå¤ļ
    -0.20
    çľĭä»ĸ
    -0.20
    aped
    -0.19
    .Fail
    -0.19
    %S
    -0.18
    äche
    -0.18
    acent
    -0.18
    å¼ıçļĦ
    -0.18
    _mA
    -0.18
    POSITIVE LOGITS
    æĢ§å¼º
    0.25
    ä¾
    0.21
    使人
    0.21
    idad
    0.19
    stuff
    0.19
    ool
    0.19
    Qualifier
    0.19
    æĹłæ¯Ķ
    0.19
    ä½ľçĶ¨
    0.19
    izable
    0.18
    Activations Density 0.140%

    No Known Activations