© 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. 2162
    Prev
    Next
    INDEX
    Explanations

    training system

    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
    ÙŃ
    -0.23
    OTH
    -0.22
    ANO
    -0.22
    umper
    -0.21
    astes
    -0.21
    idth
    -0.21
    âĪķ
    -0.21
    OTS
    -0.20
    ıp
    -0.20
    ause
    -0.20
    POSITIVE LOGITS
    ,...↵
    0.96
     ...↵
    0.93
    ,...↵↵
    0.93
    ...↵
    0.92
     ...↵↵
    0.91
    ...↵↵
    0.88
     [âĢ¦]↵↵
    0.79
     [...]↵↵
    0.76
    ...č↵
    0.75
     ..."↵
    0.75
    Activations Density 0.201%

    No Known Activations