© 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. 32114
    Prev
    Next
    INDEX
    Explanations

    Pro/Con or lists with hyphens

    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
    escu
    -0.07
    ogi
    -0.07
    ëĭĪëĭ¤
    -0.07
    nev
    -0.07
    ollen
    -0.07
    æĭ¦
    -0.07
    .temp
    -0.07
    ç¡Ŀéħ¸çĽIJ
    -0.06
    ous
    -0.06
    éĢŁéĢĴ
    -0.06
    POSITIVE LOGITS
    好åij¢
    0.08
    {{{
    0.07
    ä¹İ
    0.07
    \Foundation
    0.07
    å¾·éŁ³
    0.07
    oins
    0.07
    itam
    0.07
    ä¹ĭä¹ħ
    0.07
    ROME
    0.06
    RLF
    0.06
    Activations Density 0.020%

    No Known Activations