© 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. 17395
    Prev
    Next
    INDEX
    Explanations

    recursive factorials

    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
    å®Ľ
    -0.07
    ä¸ĭå®ļ
    -0.07
    aye
    -0.07
    nitz
    -0.06
    ä¸įå¿į
    -0.06
    omin
    -0.06
    Ñīика
    -0.06
    çĻ¾èĬ±
    -0.06
    _cs
    -0.06
    berge
    -0.06
    POSITIVE LOGITS
    zero
    0.10
    ä¸ºéĽ¶
    0.09
     zero
    0.09
    鼶
    0.09
     Zero
    0.09
     trivial
    0.08
    _zero
    0.08
    æĥŁæľī
    0.08
    éĢĴå½Ĵ
    0.08
     recursively
    0.08
    Activations Density 0.073%

    No Known Activations