© 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. 1639
    Prev
    Next
    INDEX
    Explanations

    awards, nominations, candidates

    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
     Rendering
    -0.24
     fog
    -0.24
     reproduction
    -0.23
     rearr
    -0.22
    -preview
    -0.22
     regulator
    -0.22
     contr
    -0.22
     Coloring
    -0.21
    <unsigned
    -0.21
    engu
    -0.21
    POSITIVE LOGITS
    æıIJåIJį
    0.47
     nominations
    0.43
    åĢĻéĢī
    0.43
    åĢĻéĢī人
    0.42
     candidates
    0.38
    人éĢī
    0.37
    è¯ĦéĢī
    0.37
     candidate
    0.35
     nomination
    0.34
     submissions
    0.34
    Activations Density 0.016%

    No Known Activations