© 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. 42658
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    el
    -0.07
    æŧ
    -0.07
    æ³ī
    -0.06
    åĨ²
    -0.06
    ç§ģ
    -0.06
    æ¶ī
    -0.06
     rz
    -0.06
    /
    -0.06
     dc
    -0.06
    çŁ¥è¯Ĩ
    -0.06
    POSITIVE LOGITS
    æİ
    0.09
    ipot
    0.09
    AccessException
    0.08
    leos
    0.08
    ------+
    0.08
    æĤħ
    0.08
    åĪ©çī©
    0.08
     Uang
    0.08
    ataire
    0.08
    çĥ½
    0.08
    Activations Density 0.006%

    No Known Activations