© 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. 11051
    Prev
    Next
    INDEX
    Explanations

    multiplication or expansion of expressions

    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
    ä¸ĢåĪ°
    -0.07
    åĬłæĭ¿å¤§çļĦ
    -0.07
     Inox
    -0.07
    åı°å¤§
    -0.07
    heber
    -0.07
    æĹłéĻIJçļĦ
    -0.07
    åħĭ森
    -0.07
    Ñĸз
    -0.06
    åįĩèµ·
    -0.06
    å®ħéħį
    -0.06
    POSITIVE LOGITS
    ORT
    0.08
    ernels
    0.08
     darn
    0.07
    ÙĦاء
    0.07
    ueil
    0.07
    AttributeValue
    0.07
    OURNAL
    0.07
    ortes
    0.07
    ukah
    0.07
    struments
    0.06
    Activations Density 0.006%

    No Known Activations