© 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. 57791
    Prev
    Next
    INDEX
    Explanations

    tickets (X-days)

    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
    _TRA
    -0.08
    imba
    -0.08
    ظÙĩ
    -0.08
    asang
    -0.07
    kje
    -0.07
    ieben
    -0.07
    credi
    -0.07
    laut
    -0.07
    :hidden
    -0.07
    nies
    -0.07
    POSITIVE LOGITS
    ery
    0.07
    èĭĹ
    0.07
    ERC
    0.07
    uch
    0.06
    <|fim_suffix|>
    0.06
    lobber
    0.06
    æīĵçļĦ
    0.06
    stand
    0.06
    erry
    0.06
     earm
    0.06
    Activations Density 0.002%

    No Known Activations