© 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. 2046
    Prev
    Next
    INDEX
    Explanations

    contenders and votes

    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
     instructed
    -0.27
    controls
    -0.26
     Costs
    -0.25
    shield
    -0.24
    equipment
    -0.24
    temporary
    -0.24
    Controls
    -0.24
     Efficiency
    -0.24
     repl
    -0.24
     equipments
    -0.23
    POSITIVE LOGITS
    æıIJåIJį
    0.41
    åĢĻéĢī
    0.40
    åħ¥åĽ´
    0.38
     contenders
    0.37
     candidates
    0.37
     contender
    0.37
     deserving
    0.36
     votes
    0.36
     voters
    0.35
    è¯ĦéĢī
    0.35
    Activations Density 0.025%

    No Known Activations