© 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. 39803
    Prev
    Next
    INDEX
    Explanations

    scaling and normalization

    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
    ÙĪات
    -0.07
    Dyn
    -0.07
    abilia
    -0.07
    Ta
    -0.06
    vis
    -0.06
     Rupert
    -0.06
    irt
    -0.06
     rep
    -0.06
    iable
    -0.06
    anta
    -0.06
    POSITIVE LOGITS
    _normalized
    0.09
     scaled
    0.09
    éĻ¤ä»¥
    0.09
    normalize
    0.09
    å½Ĵ
    0.08
    pace
    0.08
    Normalized
    0.08
    .free
    0.08
     Scaling
    0.08
    Scaling
    0.08
    Activations Density 0.014%

    No Known Activations