© 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. 16658
    Prev
    Next
    INDEX
    Explanations

    adenosine, ethyl, propane diol

    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
    atorium
    -0.21
    å¸Ľ
    -0.21
    ä½įç½®
    -0.20
     som
    -0.20
    ç»´
    -0.20
    ä¸ĬéĿ¢
    -0.20
    èĢĮ
    -0.19
     ab
    -0.19
    äºĨ
    -0.19
    äºĭ
    -0.18
    POSITIVE LOGITS
    åľĥ
    0.20
    纡
    0.20
    éļIJéļIJ
    0.19
    _conf
    0.19
    éļIJ约
    0.19
    èĦ¯
    0.19
    éĵĽ
    0.18
    èį£èªī称åı·
    0.18
    ·¨
    0.18
    åıĪ好åıĪå¿«
    0.18
    Activations Density 0.040%

    No Known Activations