© 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. 2475
    Prev
    Next
    INDEX
    Explanations

    weather conditions

    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
    chains
    -0.24
     Forgotten
    -0.24
    gems
    -0.22
    éĵ¿
    -0.22
    ialog
    -0.22
    è¿Ļæī¹
    -0.22
    éĵ¾æĿ¡
    -0.22
    _COMMIT
    -0.21
    ZONE
    -0.21
    erval
    -0.21
    POSITIVE LOGITS
     darkness
    0.28
     daylight
    0.27
    .sun
    0.25
    çĻ½å¤©
    0.25
    æĪĸå¤ļ
    0.24
     blackout
    0.24
     Sunny
    0.24
     sunlight
    0.24
     daytime
    0.24
    recv
    0.23
    Activations Density 0.003%

    No Known Activations