© 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. 13452
    Prev
    Next
    INDEX
    Explanations

    neuropsychiatric, neuropsychological

    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
    åºĶæĶ¶
    -0.20
    æ¡£
    -0.20
    /GPL
    -0.19
    Overrides
    -0.19
    裸
    -0.19
    DMI
    -0.19
     rh
    -0.18
    езн
    -0.18
    翯
    -0.18
    dale
    -0.18
    POSITIVE LOGITS
    qua
    0.19
    ubbo
    0.18
    America
    0.18
    èµĽ
    0.18
     Mods
    0.18
    è¿ľå¤Ħ
    0.18
    ircular
    0.17
    æµĭè¯ķ
    0.17
    贯穿
    0.17
    utility
    0.17
    Activations Density 0.004%

    No Known Activations