© 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. 29983
    Prev
    Next
    INDEX
    Explanations

    code block tokens

    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
    Vert
    -0.08
    ace
    -0.08
    ep
    -0.07
    wiki
    -0.07
    oglio
    -0.07
    ç®Ĺä»Ģä¹Ī
    -0.07
    ief
    -0.07
    ìļĶ
    -0.06
    åIJ»
    -0.06
    ipo
    -0.06
    POSITIVE LOGITS
     menti
    0.07
    isclosed
    0.07
    ashi
    0.07
     Pinh
    0.07
     fyl
    0.07
     Colonia
    0.07
    iegen
    0.07
    ernal
    0.06
     **:**
    0.06
    itti
    0.06
    Activations Density 0.063%

    No Known Activations