© 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. 45077
    Prev
    Next
    INDEX
    Explanations

    decimal numbers and fractions

    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
    åľ°åĪ©
    -0.07
    arged
    -0.07
    æĹłæĤĶ
    -0.07
    eca
    -0.07
    æij§
    -0.07
    /generated
    -0.06
    éĢ±ãģ®
    -0.06
    жда
    -0.06
    è¾ĥè½»
    -0.06
    çŃł
    -0.06
    POSITIVE LOGITS
    çĻ¾åĪĨä¹ĭ
    0.08
    ç¸
    0.08
    amay
    0.07
    decimal
    0.07
    кÑĥÑĢÑģ
    0.07
    ีà¹īยว
    0.07
    å½»
    0.07
    mdi
    0.07
    éĺ¿åħĭ
    0.06
    ä¸ĩåĪĨ
    0.06
    Activations Density 0.002%

    No Known Activations