© 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. 2185
    Prev
    Next
    INDEX
    Explanations

    schedule and program components

    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
    ếm
    -0.22
     lump
    -0.22
    ä¸ľè¥¿
    -0.22
    åĿij
    -0.21
    æ·±å¤Ħ
    -0.21
     Quick
    -0.21
     belonging
    -0.21
    ëķħ
    -0.21
    ookies
    -0.21
     condition
    -0.20
    POSITIVE LOGITS
     schedule
    0.41
     agenda
    0.40
    schedule
    0.38
    å®īæİĴ
    0.37
    (schedule
    0.35
    agenda
    0.33
     schedules
    0.31
     Agenda
    0.30
     itinerary
    0.30
    åĨħ容
    0.30
    Activations Density 0.030%

    No Known Activations