© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1944
    Prev
    Next
    INDEX
    Explanations

    MPL

    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
    icity
    -0.24
    URED
    -0.22
    UAL
    -0.20
    mes
    -0.20
    uario
    -0.20
    ual
    -0.20
    bies
    -0.20
    寤
    -0.20
    onacci
    -0.19
    aceous
    -0.19
    POSITIVE LOGITS
    boarding
    0.29
    ering
    0.23
    ðŁı»
    0.21
    å¹ħ
    0.19
    æ¹ĸåĮº
    0.19
    fish
    0.19
    ered
    0.19
     getPage
    0.18
    -alone
    0.18
    wheel
    0.18
    Activations Density 0.002%

    No Known Activations