© 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. 11512
    Prev
    Next
    INDEX
    Explanations

    color, shape, or texture descriptors

    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
     Kurd
    -0.20
    è¢ħ
    -0.20
    享åıĹåĪ°
    -0.18
     Lal
    -0.18
    gable
    -0.18
    %i
    -0.18
    Containers
    -0.18
    bearer
    -0.17
    è°ĭ
    -0.17
    loat
    -0.17
    POSITIVE LOGITS
    asel
    0.20
    å¤ļ彩
    0.20
    æł·çļĦ
    0.19
    endent
    0.19
    ipple
    0.18
    åħī彩
    0.18
    æ±ľ
    0.18
    å»¶æľŁ
    0.18
    aqu
    0.18
    æ²¹èħ»
    0.18
    Activations Density 0.021%

    No Known Activations