© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22753
    Prev
    Next
    INDEX
    Explanations

    Link to post

    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
    为äºĨèĥ½
    -0.07
    å¯Ħ
    -0.07
    彩
    -0.07
    orton
    -0.06
    lach
    -0.06
    顺
    -0.06
    etal
    -0.06
    மி
    -0.06
    merc
    -0.06
    erval
    -0.06
    POSITIVE LOGITS
    leys
    0.09
    ä¸Ń人
    0.08
    gör
    0.08
    sius
    0.08
    leigh
    0.08
    èİĺ
    0.08
    gid
    0.08
    ä¸ŃåĽ½å®¶
    0.08
    sgi
    0.07
    åĨ°å±±
    0.07
    Activations Density 0.006%

    No Known Activations