© 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. 1004
    Prev
    Next
    INDEX
    Explanations

    competitions and names

    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
     muzzle
    -0.25
    éļıæīĭ
    -0.25
    lox
    -0.24
    éģĭåĭķ
    -0.24
    createView
    -0.24
    .Tx
    -0.24
    \Mapping
    -0.23
    麽
    -0.23
    çĸ¼
    -0.22
    ListModel
    -0.22
    POSITIVE LOGITS
    çŃĶé¢ĺ
    0.34
    çĶµè§Ĩ
    0.30
    çŃĶ
    0.30
    çĮľ
    0.28
     game
    0.28
    -question
    0.28
     contestant
    0.27
     Audience
    0.27
    _bonus
    0.27
     scoring
    0.26
    Activations Density 0.009%

    No Known Activations