© 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. 47589
    Prev
    Next
    INDEX
    Explanations

    photosynthesis

    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
    ÚĨار
    -0.09
    ForKey
    -0.08
    edList
    -0.08
     rasse
    -0.08
    åĴĮæĸ¹æ³ķ
    -0.08
    ä¸İæĸ¹æ³ķ
    -0.07
    ìĤ¬íķŃ
    -0.07
     гÑĥманиÑĤаÑĢ
    -0.07
    adir
    -0.07
     pij
    -0.07
    POSITIVE LOGITS
    -related
    0.07
    omon
    0.07
    æķĪçİĩé«ĺ
    0.07
    -derived
    0.07
    -ready
    0.06
    -induced
    0.06
    lit
    0.06
    ï¸İ
    0.06
    缸åħ³åĨħ容
    0.06
    -active
    0.06
    Activations Density 0.008%

    No Known Activations