© 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. 24296
    Prev
    Next
    INDEX
    Explanations

    belief in

    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
    ymb
    -0.07
    иг
    -0.07
    iled
    -0.07
    ophone
    -0.07
    obi
    -0.07
    gle
    -0.07
    mlung
    -0.07
    imal
    -0.06
    sob
    -0.06
    tere
    -0.06
    POSITIVE LOGITS
    vedere
    0.09
    èĩªå·±æĺ¯
    0.09
     bahwa
    0.08
    åĬ¨æijĩ
    0.08
    èĢħ们
    0.08
     adanya
    0.08
    worthy
    0.08
     rằng
    0.08
    éĵĽ
    0.08
    å·²ä¹ħçļĦ
    0.08
    Activations Density 0.032%

    No Known Activations