© 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. 10254
    Prev
    Next
    INDEX
    Explanations

    code generation directives

    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
    ddit
    -0.09
     tulev
    -0.09
    alah
    -0.09
    ugas
    -0.09
     wir
    -0.09
    踵
    -0.08
     inilah
    -0.08
    ież
    -0.08
    ativi
    -0.08
    utri
    -0.08
    POSITIVE LOGITS
    ringe
    0.06
    enko
    0.06
    åħ¶èĩªçĦ¶
    0.06
     ben
    0.05
    em
    0.05
     ðŁij
    0.05
    Mods
    0.05
    scribe
    0.05
    åıĭ好
    0.05
    ewhat
    0.05
    Activations Density 0.001%

    No Known Activations