© 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. 25630
    Prev
    Next
    INDEX
    Explanations

    sequence separators

    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
    è£ħåľ¨
    -0.08
    åĩĢåĪ©
    -0.07
    terer
    -0.07
    åIJİèĢħ
    -0.07
    éĺµé£İ
    -0.06
    olim
    -0.06
    ress
    -0.06
    akse
    -0.06
    asha
    -0.06
    ìŀij
    -0.06
    POSITIVE LOGITS
    pra
    0.08
    lend
    0.08
    Uid
    0.08
    Ïħνα
    0.08
    çĻ½çŁ³
    0.07
    ÑĢин
    0.07
    inken
    0.07
    åħ¥éĩij
    0.07
    åĸ«
    0.07
    éĩĩ
    0.07
    Activations Density 0.095%

    No Known Activations