© 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. 26713
    Prev
    Next
    INDEX
    Explanations

    roman numeral iii or oxidation states

    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
    åĩij
    -0.09
    =Y
    -0.09
    åĵ½
    -0.08
    untr
    -0.08
    Å¡ek
    -0.08
    ietf
    -0.08
    arger
    -0.08
    atici
    -0.08
    åħ¨éĥ¨è¯Ħ论
    -0.08
    ķĮ
    -0.08
    POSITIVE LOGITS
    è·ĭ
    0.07
    çĽ¸å¯¹è¾ĥé«ĺ
    0.06
    Embedded
    0.06
    0.06
     oxidation
    0.06
     (-
    0.06
    isen
    0.06
     embedded
    0.06
     average
    0.06
    (-
    0.06
    Activations Density 0.001%

    No Known Activations