© 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. 15962
    Prev
    Next
    INDEX
    Explanations

    copyright or license information

    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
    resses
    -0.07
    ILED
    -0.07
    vertis
    -0.07
    [sizeof
    -0.07
    ारा
    -0.07
    nieuw
    -0.07
    ////////////////////////////////////////////////////////////////////////////////////////////////
    -0.06
    rash
    -0.06
    æŶåĢĻ
    -0.06
    ting
    -0.06
    POSITIVE LOGITS
    æīįåŃIJ
    0.07
    edata
    0.07
    Ø©
    0.07
    ças
    0.07
    ¬
    0.07
    chter
    0.07
    ça
    0.07
    ·
    0.07
    çĶ«
    0.07
     fundos
    0.07
    Activations Density 0.002%

    No Known Activations