© 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. 27674
    Prev
    Next
    INDEX
    Explanations

    shutting down

    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
    umph
    -0.10
    pum
    -0.10
    {{$
    -0.09
    auta
    -0.09
    ä¸Ģè¯ķ
    -0.09
    RequestBody
    -0.08
    haus
    -0.08
    enburg
    -0.08
    å¨ĥ
    -0.08
    igger
    -0.08
    POSITIVE LOGITS
    åħħ
    0.07
    inte
    0.07
    åºĶ该æĺ¯
    0.07
    oc
    0.06
    èī
    0.06
    z
    0.06
    s
    0.06
    èĩ³
    0.06
     Instead
    0.06
    oro
    0.06
    Activations Density 0.002%

    No Known Activations