© 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. 1400
    Prev
    Next
    INDEX
    Explanations

    time and daylight

    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
     chalk
    -0.23
    åħĭæľį
    -0.23
    æ²ī
    -0.23
    çĤ·
    -0.22
    =line
    -0.22
    éĤij
    -0.22
     abl
    -0.22
    anax
    -0.22
     noble
    -0.21
     Curriculum
    -0.21
    POSITIVE LOGITS
     season
    0.26
    atism
    0.25
    uary
    0.25
    ·»
    0.23
     Meteor
    0.23
     seasons
    0.22
    åĽ½éĻħæľºåľº
    0.22
    semester
    0.22
    æŶèĬĤ
    0.22
    åĮĹ京æŶéĹ´
    0.22
    Activations Density 0.001%

    No Known Activations