© 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. 14438
    Prev
    Next
    INDEX
    Explanations

    admit or confess

    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
    åij£
    -0.22
    ä½ķå¿ħ
    -0.22
    _mD
    -0.21
    mere
    -0.20
    UAGE
    -0.20
    èİ«åIJįåħ¶
    -0.20
     ÑģкоÑĢо
    -0.20
    AÄŀ
    -0.19
    _cpus
    -0.19
    åºĶ该æĢİä¹Ī
    -0.19
    POSITIVE LOGITS
     peek
    0.23
    peek
    0.23
    i
    0.21
    æĪijåĸľæ¬¢
    0.21
    æĪij没æľī
    0.21
     candid
    0.20
    :
    0.20
    æºľ
    0.20
     though
    0.20
     mixed
    0.20
    Activations Density 0.014%

    No Known Activations