© 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. 15347
    Prev
    Next
    INDEX
    Explanations

    URL, domain, or code segments

    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
    вл
    -0.07
     })(
    -0.07
    rega
    -0.07
    ìĹ°
    -0.07
    ÎĹΣ
    -0.07
    åĽ°æī°
    -0.07
    UNET
    -0.07
    olda
    -0.07
    ROTO
    -0.06
    RAIN
    -0.06
    POSITIVE LOGITS
     versus
    0.09
    ä¹ĭç±»çļĦ
    0.08
     rather
    0.08
    çļĦ缸åħ³åĨħ容
    0.08
    èĢĮéĿŀ
    0.07
    ä¹ĭç±»
    0.07
    èĢĮä¸įæĺ¯
    0.07
    {}\
    0.07
     plutôt
    0.07
    ...,
    0.06
    Activations Density 0.075%

    No Known Activations