© 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. 20295
    Prev
    Next
    INDEX
    Explanations

    exception or io

    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
    éľĢè¦ģä¸Ģ个
    -0.08
    isFunction
    -0.08
    trup
    -0.08
    parg
    -0.08
    etas
    -0.08
    utc
    -0.08
    ciso
    -0.08
    欲滴
    -0.07
    ôt
    -0.07
    zb
    -0.07
    POSITIVE LOGITS
    婧
    0.07
    u
    0.07
    en
    0.06
    |
    0.06
    ä¹ĥ
    0.06
    ðŁ
    0.06
    åķĬ
    0.06
    enom
    0.06
    çĶŁ
    0.06
    èĩ´
    0.06
    Activations Density 0.002%

    No Known Activations