© 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. 1518
    Prev
    Next
    INDEX
    Explanations

    unit, fee, device, sensor, shape, tool, car, footnote

    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
    ÑĩÑĢежден
    -0.25
    ãģ®ãģ¯
    -0.24
    NESS
    -0.24
    InstanceOf
    -0.24
     pursuing
    -0.23
     punishing
    -0.23
     Antar
    -0.23
     victorious
    -0.22
    ÑĩÑĢ
    -0.22
     upcoming
    -0.22
    POSITIVE LOGITS
    sWith
    0.56
    们
    0.55
    swith
    0.55
    们çļĦ
    0.52
    åĢij
    0.49
    们éĥ½
    0.46
    sto
    0.45
    sthrough
    0.42
    (s
    0.40
    ëĵ¤ìĿĢ
    0.37
    Activations Density 1.354%

    No Known Activations