© 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. 12068
    Prev
    Next
    INDEX
    Explanations

    unmet need or coverage

    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
    éĢı
    -0.21
    åįģåŃĹ
    -0.19
    ç´§åĩij
    -0.19
    èµī
    -0.18
    为äºĨ让
    -0.18
    åijĭ
    -0.18
    没è§ģè¿ĩ
    -0.18
    sharing
    -0.18
    selection
    -0.18
    å¸Ŀ
    -0.18
    POSITIVE LOGITS
     полÑĥ
    0.21
    å¾ĹåĪ°æľīæķĪ
    0.20
    缺失
    0.20
    иÑĤелÑı
    0.20
    MISS
    0.20
    asics
    0.20
     VÆ°Æ¡ng
    0.19
    oyer
    0.19
     ÑĩаÑģÑĤи
    0.19
    æ¼ł
    0.19
    Activations Density 0.031%

    No Known Activations