© 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. 27511
    Prev
    Next
    INDEX
    Explanations

    proportionality and scaling

    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
    _vectors
    -0.08
     toggle
    -0.07
     Bris
    -0.07
    è´°
    -0.07
    çīĩåĪ»
    -0.07
     Pret
    -0.07
    irma
    -0.07
    abili
    -0.07
    bitset
    -0.07
    çīĪ
    -0.07
    POSITIVE LOGITS
     exponent
    0.11
     logarith
    0.08
     fal
    0.08
    æī¾åĪ°èĩªå·±
    0.08
    å¾ĭ
    0.07
     exponential
    0.07
     dependence
    0.07
    -log
    0.07
     extrapol
    0.07
    .log
    0.07
    Activations Density 0.025%

    No Known Activations