© 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. 13239
    Prev
    Next
    INDEX
    Explanations

    coat, seal, protection

    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
    éĹ¹
    -0.21
    etes
    -0.20
    iets
    -0.20
    èĨĤ
    -0.20
    atedRoute
    -0.20
    弧
    -0.19
    秧
    -0.19
    avic
    -0.19
    romosome
    -0.19
    igne
    -0.19
    POSITIVE LOGITS
    å®ŀå¹²
    0.28
    ä¿ĿæĬ¤
    0.27
    åijµæĬ¤
    0.25
    ä¿ĿèŃ·
    0.24
     finish
    0.24
    éĺ²æ°´
    0.24
     заÑīиÑĤ
    0.24
     protect
    0.24
    ä¸Ģå±Ĥ
    0.22
     заÑīиÑĤÑĭ
    0.22
    Activations Density 0.021%

    No Known Activations