© 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. 28917
    Prev
    Next
    INDEX
    Explanations

    solubility, capacity, concentration

    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
    ãģ¤ãģ¶
    -0.08
    åªĽ
    -0.07
    èĦĩ
    -0.07
    TERNAL
    -0.07
    ÙĦاÙģ
    -0.07
    llum
    -0.07
    onti
    -0.07
     électriques
    -0.07
     internally
    -0.07
     moments
    -0.07
    POSITIVE LOGITS
    åįģåħ¨
    0.08
     solvent
    0.08
    溶解
    0.08
     capacity
    0.08
    _CAPACITY
    0.07
    capacity
    0.07
     sher
    0.07
    çĶ©
    0.07
    åĨ¬å¤©çļĦ
    0.07
    容纳
    0.07
    Activations Density 0.003%

    No Known Activations