© 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. 1879
    Prev
    Next
    INDEX
    Explanations

    service of the

    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
     ISO
    -0.23
    tring
    -0.23
     SI
    -0.23
    æĬ¼
    -0.23
    æľįè£ħ
    -0.22
     Automotive
    -0.21
    EEK
    -0.21
     Auto
    -0.21
    TI
    -0.21
     Suspension
    -0.21
    POSITIVE LOGITS
    翳
    0.25
    交æĺĵå¹³åı°
    0.23
    idon
    0.23
    çĶ¥
    0.23
    idelity
    0.22
    sst
    0.22
    ä¸ī家
    0.21
    çļĭ
    0.21
    raith
    0.21
     sidelines
    0.21
    Activations Density 0.005%

    No Known Activations