© 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. 13174
    Prev
    Next
    INDEX
    Explanations

    LV AN

    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
    åĨħåľ°
    -0.18
    æ®Ĩ
    -0.18
    oton
    -0.18
    /rem
    -0.18
    -span
    -0.17
     Warwick
    -0.17
    iji
    -0.17
    uen
    -0.17
    è£ħä¿®
    -0.17
    åħħåĢ¼
    -0.16
    POSITIVE LOGITS
    hands
    0.23
    åıĮæīĭ
    0.20
    gers
    0.20
    ell
    0.19
     Amb
    0.19
    á»Ĭ
    0.19
    é¦į
    0.18
    ánd
    0.18
    å¤ĸå¥Ĺ
    0.18
    Õ¦
    0.18
    Activations Density 0.001%

    No Known Activations