© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17617
    Prev
    Next
    INDEX
    Explanations

    self-talk and personal reflection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gom
    -0.08
     Punch
    -0.07
    ãĤĦãĤĬ
    -0.07
    sche
    -0.07
     dismiss
    -0.07
    amak
    -0.07
    åĪĽæĸ°èĥ½åĬĽ
    -0.07
    arat
    -0.06
    ä¸įæŃ¢
    -0.06
     appointed
    -0.06
    POSITIVE LOGITS
    ä¸Ģæ¯Ķ
    0.07
    éħ¿
    0.07
     Shame
    0.07
    thumb
    0.07
    änder
    0.07
     plutôt
    0.07
    -thumb
    0.07
     instead
    0.07
    èĢĮä¸įæĺ¯
    0.07
    æľĢç»ĪåıĹçĽĬ
    0.07
    Activations Density 0.001%

    No Known Activations