© 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. 8442
    Prev
    Next
    INDEX
    Explanations

    alkaline battery level

    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
    åĶ¯
    -0.08
    è¿«
    -0.07
    éŃĦ
    -0.07
    ommer
    -0.07
    azza
    -0.07
    å®ŀçī©
    -0.06
    awang
    -0.06
    iasi
    -0.06
    /extensions
    -0.06
    对人çļĦ
    -0.06
    POSITIVE LOGITS
    Neutral
    0.08
    neutral
    0.08
     ìłĦíķ´
    0.08
    alk
    0.08
    åĪ°è¿ĩ
    0.07
     alkal
    0.07
    utral
    0.07
    ä¸Ģ段æŶéĹ´åIJİ
    0.07
    碱æĢ§
    0.07
    oba
    0.07
    Activations Density 0.001%

    No Known Activations