© 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. 39174
    Prev
    Next
    INDEX
    Explanations

    is known

    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
    liable
    -0.07
    :len
    -0.07
    FromBody
    -0.07
    éĻµåĽŃ
    -0.07
    RequestMethod
    -0.07
    åĪĨåĪ°
    -0.07
    è¿ĻçĤ¹
    -0.07
    боÑĢ
    -0.07
    :true
    -0.07
    unst
    -0.07
    POSITIVE LOGITS
    ata
    0.07
    isht
    0.07
    æŀĦ
    0.07
     Operator
    0.07
    ([\
    0.07
     ÑģоглаÑģно
    0.07
    å°¾
    0.07
    åĺī
    0.06
    Operator
    0.06
    iter
    0.06
    Activations Density 0.004%

    No Known Activations