© 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. 12769
    Prev
    Next
    INDEX
    Explanations

    markers followed by R or b

    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
    unar
    -0.07
    undance
    -0.07
    »
    -0.07
    \n
    -0.07
    ference
    -0.07
    æĥŁ
    -0.06
    åıªèĥ½
    -0.06
    _UPDATED
    -0.06
    çĦ¶
    -0.06
    ç¿Ķ
    -0.06
    POSITIVE LOGITS
    à¹Īà¸Ńà¸ĩ
    0.08
    <|repo_name|>
    0.07
    év
    0.07
    鼷æĸ¯
    0.07
    ¿IJ
    0.07
    xeda
    0.07
    åĩºæĸ°
    0.07
    cams
    0.07
    ellis
    0.07
    ]int
    0.06
    Activations Density 0.155%

    No Known Activations