© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 45710
    Prev
    Next
    INDEX
    Explanations

    consider questions

    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
    enticate
    -0.11
    smith
    -0.08
    elige
    -0.08
    elling
    -0.08
    รà¸ĩà¸Ħà¹Į
    -0.08
    orsk
    -0.08
    iculty
    -0.07
    کارÛĮ
    -0.07
    rome
    -0.07
    /twitter
    -0.07
    POSITIVE LOGITS
    ered
    0.13
    åĪ°çĽ®åīį
    0.11
    erp
    0.09
    erne
    0.09
    erb
    0.09
    aat
    0.08
     whether
    0.08
    amanan
    0.08
     matang
    0.08
    åij¨åĪ°
    0.08
    Activations Density 0.043%

    No Known Activations