© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 623
    Prev
    Next
    INDEX
    Explanations

    discharge lamps

    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
    ðŁ§
    -0.26
     comeback
    -0.24
     whatsapp
    -0.24
    leston
    -0.23
    udget
    -0.23
     Redemption
    -0.23
     Receipt
    -0.23
    checksum
    -0.23
    defense
    -0.23
     Wallet
    -0.22
    POSITIVE LOGITS
     radiation
    0.32
    è¾IJå°Ħ
    0.32
     radi
    0.32
     overhead
    0.32
     radiant
    0.28
    çĤī
    0.28
    çģ¯åħī
    0.28
    æ°Ļ
    0.28
     coils
    0.28
    radi
    0.28
    Activations Density 0.037%

    No Known Activations