© 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. 13858
    Prev
    Next
    INDEX
    Explanations

    is called

    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
    .streaming
    -0.20
    åĨį说
    -0.20
     latest
    -0.18
    对ä»ĸ
    -0.18
    ä¸Ĭ次
    -0.18
    agos
    -0.18
    æłı缮
    -0.17
    è§ģæķĪ
    -0.17
    å¿ĥæĥ³
    -0.17
    ä¸į妨
    -0.17
    POSITIVE LOGITS
    被称为
    0.28
    被èªī为
    0.20
    第ä¸Ģéĥ¨
    0.20
     Breaking
    0.20
    Breaking
    0.19
    Located
    0.19
    chor
    0.18
    èijĹåIJįçļĦ
    0.18
     Typ
    0.18
    åģĩè£ħ
    0.18
    Activations Density 0.943%

    No Known Activations