© 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. 2961
    Prev
    Next
    INDEX
    Explanations

    patent numbers

    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
     federal
    -0.25
     closet
    -0.24
    PTR
    -0.23
     federally
    -0.23
     virtual
    -0.23
    è°Ĩ
    -0.23
     closets
    -0.22
     granite
    -0.21
    ®
    -0.21
    orton
    -0.21
    POSITIVE LOGITS
     organised
    0.29
     specialised
    0.27
     recognised
    0.26
     Aluminium
    0.25
    centre
    0.25
    ised
    0.24
     ÈĻi
    0.23
    ĵį
    0.23
     analysed
    0.23
     colourful
    0.23
    Activations Density 0.016%

    No Known Activations