© 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. 14450
    Prev
    Next
    INDEX
    Explanations

    add to

    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
    uet
    -0.20
    bum
    -0.20
    åĩºå¤Ħ
    -0.19
    ina
    -0.18
    ingo
    -0.18
    olin
    -0.18
    å¼Ģå±ķ
    -0.17
    oj
    -0.17
    zin
    -0.17
    ibel
    -0.17
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.28
    /sub
    0.23
    åİŁæľīçļĦ
    0.23
    itive
    0.21
    çİ°æľīçļĦ
    0.21
    è¦ģèĢĥèĻij
    0.20
    äºĨèĩªå·±çļĦ
    0.19
    å®ĮåĸĦ
    0.18
    /Sub
    0.18
    çļĦæĦŁåıĹ
    0.18
    Activations Density 0.025%

    No Known Activations