© 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. 57629
    Prev
    Next
    INDEX
    Explanations

    code syntax 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
    waard
    -0.07
    _FOREACH
    -0.07
    çī¹ç§įåħµ
    -0.07
    åħ¶éĹ´
    -0.07
     suivante
    -0.07
    è¿
    -0.07
     atIndex
    -0.07
    acent
    -0.07
    沧海
    -0.06
    ancellable
    -0.06
    POSITIVE LOGITS
    ovel
    0.08
    uled
    0.07
    ίο
    0.07
    森
    0.07
     ÙĪرد
    0.07
    _sal
    0.07
    anson
    0.07
    èĶĵ
    0.06
    TERS
    0.06
    é«ĺåĪĨ
    0.06
    Activations Density 0.004%

    No Known Activations