© 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. 34604
    Prev
    Next
    INDEX
    Explanations

    halogens and phosphorus compounds

    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
    nable
    -0.10
    ##_
    -0.08
    Ùĭ
    -0.07
    äºķçĦ¶
    -0.07
    emun
    -0.07
    riba
    -0.07
     Cosby
    -0.07
    çļĨçŁ¥
    -0.07
    éģIJ
    -0.07
    leston
    -0.06
    POSITIVE LOGITS
    ine
    0.10
    ification
    0.09
    amine
    0.09
    mér
    0.09
    ore
    0.09
    ified
    0.09
    age
    0.08
    ième
    0.08
    ï¸ı
    0.08
    iness
    0.08
    Activations Density 0.069%

    No Known Activations