© 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. 57964
    Prev
    Next
    INDEX
    Explanations

    grid edit, Engineer builds, elderly patients

    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
    @s
    -0.08
    @a
    -0.07
    oir
    -0.07
    otionEvent
    -0.07
    .defaults
    -0.07
    å¼ŁåħĦ
    -0.07
    jav
    -0.07
    eix
    -0.07
     defaults
    -0.07
    髦
    -0.07
    POSITIVE LOGITS
    istri
    0.07
    Rpc
    0.07
     Äijiá»ĩu
    0.06
    èĢĮæѤæŶ
    0.06
    好åķĬ
    0.06
    湿
    0.06
    è½»æŁĶ
    0.06
    .RED
    0.06
     perfor
    0.06
    çĨŁ
    0.06
    Activations Density 0.131%

    No Known Activations