© 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. 12242
    Prev
    Next
    INDEX
    Explanations

    required by

    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
    bing
    -0.17
    åĦ¿
    -0.16
     à¹Ĩ
    -0.16
    rique
    -0.16
    iliation
    -0.15
    /or
    -0.15
    iors
    -0.15
    ç¾¤å²Ľ
    -0.15
    ored
    -0.15
    ì§ľ
    -0.15
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.23
    èĩ¾
    0.23
    uset
    0.22
    ment
    0.22
    ities
    0.20
    ance
    0.19
    lessly
    0.19
    orate
    0.18
    ä¸įéľĢè¦ģ
    0.17
    mente
    0.17
    Activations Density 0.089%

    No Known Activations