© 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. 3616
    Prev
    Next
    INDEX
    Explanations

    neutral descriptive words

    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
    Fmt
    -0.08
    áĥIJáĥľáĥĺ
    -0.08
    å°ıåĪ°
    -0.08
    ouz
    -0.08
    awali
    -0.07
     devid
    -0.07
    `=
    -0.07
    âĢ§
    -0.07
    `.`
    -0.07
     ($.
    -0.07
    POSITIVE LOGITS
    ???
    0.08
    èĢĮä¸įæĺ¯
    0.08
    åIJĹ
    0.08
     instead
    0.07
    ards
    0.07
     rather
    0.07
    ????
    0.07
    ??
    0.07
     CPC
    0.06
    N
    0.06
    Activations Density 0.064%

    No Known Activations