© 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. 57685
    Prev
    Next
    INDEX
    Explanations

    heating and plasticizing materials

    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
    yer
    -0.09
    éĺ²éĽ·
    -0.08
     koc
    -0.07
    EFAULT
    -0.07
    urer
    -0.07
    chern
    -0.07
    ugas
    -0.07
    .filtered
    -0.07
     outraged
    -0.07
    obox
    -0.07
    POSITIVE LOGITS
    软åĮĸ
    0.09
    allow
    0.09
    æŁĶ
    0.08
    åħģ许
    0.08
    便äºİ
    0.08
    Allow
    0.08
    ALLOW
    0.08
    以便äºİ
    0.08
     soft
    0.08
     softened
    0.08
    Activations Density 0.105%

    No Known Activations