© 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. 31343
    Prev
    Next
    INDEX
    Explanations

    metal binding

    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
    etés
    -0.08
    inov
    -0.08
    inou
    -0.07
    æİĴæ°Ķ
    -0.07
    charted
    -0.07
    çĵ¤
    -0.07
    çĩĥ
    -0.07
    dain
    -0.07
     Kud
    -0.07
    vál
    -0.07
    POSITIVE LOGITS
    éĩįéĩijå±ŀ
    0.09
    èŀ
    0.08
     metal
    0.08
     metallo
    0.08
    éĶ°
    0.08
    çŁ¿çī©è´¨
    0.08
    å¾®éĩıåħĥç´ł
    0.08
     metals
    0.08
     bronze
    0.08
     binding
    0.08
    Activations Density 0.143%

    No Known Activations