© 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. 33396
    Prev
    Next
    INDEX
    Explanations

    classified by different criteria

    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
    cesa
    -0.10
    ErrorException
    -0.09
    潺
    -0.08
    æĹ¥çĶµ
    -0.08
    çĤ¹æѤ
    -0.08
    ModelError
    -0.08
    بÙĪÙĦ
    -0.08
    zicht
    -0.07
    reich
    -0.07
     espos
    -0.07
    POSITIVE LOGITS
    èĢĮå¾ĹåIJį
    0.09
     distinguished
    0.08
     distinguishing
    0.08
    åı¯åĪĨ为
    0.07
    åIJ¦
    0.06
    主è¦ģåĪĨ为
    0.06
     whether
    0.06
     distinction
    0.06
    æĺĤ
    0.06
    å¾ĹåIJį
    0.06
    Activations Density 0.092%

    No Known Activations