© 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. 9462
    Prev
    Next
    INDEX
    Explanations

    later or below

    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
    azes
    -0.08
    ")),
    -0.08
    ãģ£ãģĵ
    -0.07
    Ïħμα
    -0.07
    adf
    -0.07
    åĽłæŃ¤åľ¨
    -0.07
    oload
    -0.07
     ç§ģ
    -0.07
    osan
    -0.07
    ttp
    -0.07
    POSITIVE LOGITS
     later
    0.11
    later
    0.10
     Later
    0.10
    Later
    0.08
    åħĪçľĭ
    0.08
    æļĤ
    0.08
     позже
    0.07
    åħĪ
    0.07
     später
    0.07
     ÙĦاØŃÙĤ
    0.06
    Activations Density 0.072%

    No Known Activations