© 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. 42067
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    acher
    -0.06
    ä¸įæĪIJ
    -0.06
    ron
    -0.06
    è°Ī
    -0.06
    fle
    -0.06
    人å¤ļ
    -0.06
    /net
    -0.06
    (optional
    -0.06
    .tc
    -0.06
    éī´
    -0.06
    POSITIVE LOGITS
    entials
    0.07
    irl
    0.07
    umeurs
    0.07
    _Utils
    0.07
    _tF
    0.07
    evos
    0.07
    _CLEAN
    0.07
    utterstock
    0.07
    indre
    0.07
    åħ¶èº«
    0.07
    Activations Density 0.002%

    No Known Activations