© 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. 33061
    Prev
    Next
    INDEX
    Explanations

    end of code blocks

    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
    ients
    -0.08
    湿润
    -0.06
    è´¨
    -0.06
    lak
    -0.06
    ient
    -0.06
    o
    -0.06
    exact
    -0.06
    ek
    -0.06
    egree
    -0.06
    idis
    -0.06
    POSITIVE LOGITS
    åIJ¦
    0.09
    _ATTRIB
    0.08
    COMMAND
    0.08
    engg
    0.08
    oulos
    0.08
    èĥ¤
    0.08
    éĤ£æĺ¯åĽłä¸º
    0.08
    åĽ±
    0.08
    龸éģĵ
    0.07
    OrNil
    0.07
    Activations Density 0.084%

    No Known Activations