© 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. 1812
    Prev
    Next
    INDEX
    Explanations

    function or usage

    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
    OfWork
    -0.30
     looming
    -0.25
    æĥ³åİ»
    -0.25
    æĸ°æĿIJæĸĻ
    -0.24
    ufs
    -0.24
    .isSelected
    -0.24
    (Have
    -0.24
    "urls
    -0.24
    åĵģ
    -0.23
    (KP
    -0.23
    POSITIVE LOGITS
     function
    0.38
    åĩ½æķ°
    0.36
     optionally
    0.34
     Function
    0.33
     Deprecated
    0.32
     functionality
    0.32
     func
    0.32
     returns
    0.31
     Usage
    0.29
     usage
    0.29
    Activations Density 0.653%

    No Known Activations