© 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. 20048
    Prev
    Next
    INDEX
    Explanations

    drainage and grain boundaries

    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
     nhau
    -0.09
    cal
    -0.09
    s
    -0.08
    schild
    -0.08
    днÑı
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    ional
    -0.07
    schein
    -0.07
    ãĢħãģ«
    -0.07
    gers
    -0.07
    POSITIVE LOGITS
    веÑģÑĤ
    0.08
    enburg
    0.08
    åijIJ
    0.08
    ãĥ§
    0.08
    roads
    0.08
    buster
    0.08
    enberg
    0.08
    áŁĭ
    0.08
    iffs
    0.08
    uba
    0.07
    Activations Density 0.074%

    No Known Activations