© 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. 8622
    Prev
    Next
    INDEX
    Explanations

    aman 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
    çĶ·åĦ¿
    -0.07
    èŀŁ
    -0.07
     Balt
    -0.06
    AL
    -0.06
    olini
    -0.06
    inna
    -0.06
    壮
    -0.06
    /false
    -0.06
    /bower
    -0.06
    å¹³
    -0.06
    POSITIVE LOGITS
    幽幽
    0.08
     spontaneous
    0.08
    dav
    0.08
    ieg
    0.07
    ÑĪин
    0.07
     espont
    0.07
    okal
    0.07
    dex
    0.07
    åħ¥ç¾¤
    0.07
    riba
    0.07
    Activations Density 0.012%

    No Known Activations