© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63100
    Prev
    Next
    INDEX
    Explanations

    spectrometry or spectroscopy

    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
    åĪĨçļĦ
    -0.06
     rev
    -0.06
    _SEND
    -0.06
    使èĢħ
    -0.06
    åĭĩ
    -0.06
    éĢĬ
    -0.06
    仲
    -0.06
    åݦ
    -0.06
    èĪ¬çļĦ
    -0.06
    شا
    -0.06
    POSITIVE LOGITS
     Singer
    0.08
    ujan
    0.08
    çĵľæŀľ
    0.07
    ulte
    0.07
    ucha
    0.07
    oine
    0.07
    irit
    0.07
    igas
    0.07
    iste
    0.07
    éĹ®é¢ĺçļĦ
    0.07
    Activations Density 0.309%

    No Known Activations