© 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. 16124
    Prev
    Next
    INDEX
    Explanations

    sizes and shapes

    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
    éĺ¿æł¹
    -0.21
    éĿłçĿĢ
    -0.19
    å¾ħ
    -0.18
    é«ĺåľ°
    -0.18
    强çĥĪ
    -0.18
    .magic
    -0.18
    _exit
    -0.18
    ä¸Ĭä¸ĭ游
    -0.18
    çľĭä»ĸ
    -0.18
    .setParent
    -0.17
    POSITIVE LOGITS
    çīĪ
    0.24
    åİļ
    0.24
    -friendly
    0.22
    ç»ıçIJĨ
    0.21
    大å®Ĺ
    0.21
     Overflow
    0.21
     Thick
    0.21
     roast
    0.21
    Series
    0.21
     Starr
    0.20
    Activations Density 0.014%

    No Known Activations