© 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. 13770
    Prev
    Next
    INDEX
    Explanations

    disposal and waste

    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
    èĭ±æīį
    -0.23
    nest
    -0.19
    è¦ģæľī
    -0.19
    ç®Ĺ
    -0.18
    Detach
    -0.18
    å±
    -0.18
    ategy
    -0.18
    èĩªå·±çļĦ
    -0.18
    iscal
    -0.18
    仪
    -0.17
    POSITIVE LOGITS
     ì²ĺ리
    0.22
    æľĢç»Ī
    0.21
     harmless
    0.20
     revenue
    0.20
    å¤Ħç½®
    0.19
    _final
    0.19
    вол
    0.19
     eventually
    0.19
    éĶĢæ¯ģ
    0.19
    åIJİç»Ń
    0.19
    Activations Density 0.025%

    No Known Activations