© 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. 10603
    Prev
    Next
    INDEX
    Explanations

    non-negative or positive values

    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
    trut
    -0.08
    lvl
    -0.08
    æ°Ľ
    -0.08
    ContentType
    -0.08
    ாள
    -0.08
    efs
    -0.08
    usercontent
    -0.07
    thora
    -0.07
    isin
    -0.07
    chants
    -0.07
    POSITIVE LOGITS
     positive
    0.09
    Positive
    0.09
     Positive
    0.09
    æŃ£åĢ¼
    0.09
    -negative
    0.09
    -positive
    0.09
    positive
    0.09
     positivity
    0.09
    _positive
    0.08
    .Positive
    0.08
    Activations Density 0.014%

    No Known Activations