© 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. 8281
    Prev
    Next
    INDEX
    Explanations

    exclude, except, unless, nor

    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
    ä¸įæĥľ
    -0.08
    .defaults
    -0.07
    agan
    -0.07
    umpt
    -0.07
    Millis
    -0.07
    ivin
    -0.07
    ussy
    -0.07
    uyen
    -0.07
    çĶļèĩ³
    -0.07
    ollo
    -0.07
    POSITIVE LOGITS
    unless
    0.12
     unless
    0.12
    éĻ¤éĿŀ
    0.11
    ä¾ĭå¤ĸ
    0.11
     kecuali
    0.10
     except
    0.10
    éĻ¤å¤ĸ
    0.10
     nor
    0.10
     Unless
    0.10
    except
    0.10
    Activations Density 0.111%

    No Known Activations