© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 50819
    Prev
    Next
    INDEX
    Explanations

    method or command structure

    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
    ...
    -0.08
     c
    -0.07
     w
    -0.07
    \n
    -0.06
     (
    -0.06
    -
    -0.06
    ht
    -0.06
     h
    -0.06
     $
    -0.06
     di
    -0.05
    POSITIVE LOGITS
    WithValue
    0.09
    ::__
    0.09
    poste
    0.09
    åįģåĪĨéĩįè§Ĩ
    0.09
    nheim
    0.09
    winkel
    0.09
    WithContext
    0.09
    ECTR
    0.08
    INGK
    0.08
    .prototype
    0.08
    Activations Density 0.026%

    No Known Activations