© 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. 41492
    Prev
    Next
    INDEX
    Explanations

    punctuation and delimiters

    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
    ritt
    -0.08
    /framework
    -0.07
    rita
    -0.07
    èĩªæĪIJ
    -0.06
    rig
    -0.06
     rigor
    -0.06
     rasa
    -0.06
    aidu
    -0.06
     proved
    -0.06
    ãĥ©ãĤ¤ãĥĪ
    -0.06
    POSITIVE LOGITS
    åıĬåij¨è¾¹
    0.08
    ziem
    0.07
    çľĭåĪ°è¿ĻéĩĮ
    0.07
    ç±³å¤Ħ
    0.07
    usus
    0.07
    chow
    0.07
     pobre
    0.07
    ges
    0.07
     berarti
    0.07
    åĨħ容æľī
    0.07
    Activations Density 0.007%

    No Known Activations