© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1272
    Prev
    Next
    INDEX
    Explanations

    motor neuron vs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    uci
    -0.26
    æł¼
    -0.25
    åĨĴ
    -0.23
    ä½ľä¸ºä¸Ģ个
    -0.23
    łģ
    -0.23
    ä¸įæĺ¯ä¸Ģ个
    -0.23
    Knight
    -0.23
    oppers
    -0.22
    esub
    -0.22
    åıĬ缸åħ³
    -0.22
    POSITIVE LOGITS
     vs
    0.36
     versus
    0.34
     Vs
    0.31
     processes
    0.26
    -vs
    0.26
    /non
    0.25
     counterparts
    0.25
    -only
    0.25
    è¿ĺ好
    0.24
     Essay
    0.23
    Activations Density 0.772%

    No Known Activations