© 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. 31402
    Prev
    Next
    INDEX
    Explanations

    mathematical notation involving S and Z

    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
    åħ¬çĪµ
    -0.07
    ä¾
    -0.07
    ืà¹Īà¸Ńà¸Ķ
    -0.07
    æŃ»æ´»
    -0.07
    æĪIJåĬŁåIJİåį³åı¯
    -0.07
    ãĥ¼ãĤ¸
    -0.07
    æĶ¹
    -0.06
    á»į
    -0.06
    ük
    -0.06
    library
    -0.06
    POSITIVE LOGITS
    -tm
    0.07
    ä¸Ģéĥİ
    0.07
    ÙĬÙĨÙĪ
    0.07
    æĺĨä»ij
    0.07
    å¿ħ
    0.07
    å¿ħçĦ¶
    0.07
    ÃģC
    0.07
     inevitable
    0.06
    quio
    0.06
    oces
    0.06
    Activations Density 0.007%

    No Known Activations