© 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. 12149
    Prev
    Next
    INDEX
    Explanations

    adding or multiplying

    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
    iable
    -0.09
    çļĦå·¥ä½ľæĢģ度
    -0.08
    igny
    -0.08
    essant
    -0.08
    åĨįä¸į
    -0.08
    odos
    -0.08
    çľīå±±
    -0.08
    otin
    -0.07
    möglich
    -0.07
    ÚĨار
    -0.07
    POSITIVE LOGITS
    éĢĤå½ĵçļĦ
    0.08
     appropriate
    0.07
    rud
    0.07
     appropriately
    0.07
     denomin
    0.07
    /desktop
    0.06
    ä¿Ŀè¯ģ
    0.06
    atil
    0.06
    party
    0.06
    éĢĤå½ĵ
    0.06
    Activations Density 0.004%

    No Known Activations