© 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. 14209
    Prev
    Next
    INDEX
    Explanations

    end tag

    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
    oram
    -0.08
    venge
    -0.08
    çĶŁè¾°
    -0.07
    omething
    -0.07
    iken
    -0.07
     cá»Ń
    -0.07
    åľ°å¤Ħ
    -0.07
    akest
    -0.07
    umpl
    -0.07
    åijī
    -0.07
    POSITIVE LOGITS
    /end
    0.10
    为æŃ¢
    0.08
    åĨį继ç»Ń
    0.07
    /close
    0.07
    ä¹Łä¸įåĨį
    0.07
    çĤºæŃ¢
    0.07
    äºĨä¸ĢåĪĩ
    0.07
    lass
    0.07
    allel
    0.07
    åĨįä¹Łæ²¡æľī
    0.06
    Activations Density 0.049%

    No Known Activations