© 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. 15573
    Prev
    Next
    INDEX
    Explanations

    shall

    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
    ç¿»
    -0.24
    éĢįéģ¥
    -0.22
    benh
    -0.20
     plural
    -0.20
    éĢį
    -0.19
    çĽĨåľ°
    -0.19
    带
    -0.18
     bust
    -0.18
    åıĤ
    -0.18
    å±Ģ
    -0.18
    POSITIVE LOGITS
    身å¿ĥåģ¥åº·
    0.22
    å·´æĭī
    0.22
    累累
    0.22
     SHALL
    0.20
    ä¸įå¾Ĺ
    0.20
    çī©æĸĻ
    0.20
    lias
    0.20
    æįŁå®³
    0.19
    ä¸įè¶ħè¿ĩ
    0.19
    WARE
    0.19
    Activations Density 0.901%

    No Known Activations