© 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. 38074
    Prev
    Next
    INDEX
    Explanations

    syntax for code declarations

    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
    aghan
    -0.08
    _characters
    -0.08
    åIJijè®°èĢħ
    -0.08
    _strike
    -0.08
    egner
    -0.07
    elang
    -0.07
     hog
    -0.07
    åĪ©åĻ¨
    -0.07
    å§ĵ
    -0.07
    _TERMIN
    -0.07
    POSITIVE LOGITS
    zing
    0.06
    i
    0.06
    رخ
    0.06
    efa
    0.06
    o
    0.06
    éĩijéĵ¶
    0.06
    amt
    0.06
    ç¡
    0.06
    çĶŁæ¶¯
    0.06
    t
    0.06
    Activations Density 0.151%

    No Known Activations