© 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. 12212
    Prev
    Next
    INDEX
    Explanations

    rabbi

    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
    ingly
    -0.19
    aneous
    -0.18
    chart
    -0.18
    /testify
    -0.17
    ervo
    -0.17
    模ç³Ĭ
    -0.17
    voy
    -0.16
    loan
    -0.16
    roy
    -0.16
    lass
    -0.15
    POSITIVE LOGITS
    esses
    0.23
    们çļĦ
    0.23
    ä½Ĩä¸įéĻIJäºİ
    0.18
    ëĭĺ
    0.18
    åĢij
    0.17
    -major
    0.17
    bing
    0.17
    ðŁı¼
    0.17
    âĢİ
    0.17
    åĬ©çIJĨ
    0.17
    Activations Density 0.005%

    No Known Activations