© 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. 61782
    Prev
    Next
    INDEX
    Explanations

    similarity, above, preceding

    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
    illet
    -0.06
    tero
    -0.06
    ãĤ¸
    -0.06
    lagt
    -0.06
    ç¡®æľī
    -0.05
    fol
    -0.05
    emann
    -0.05
     array
    -0.05
    .mp
    -0.05
    af
    -0.05
    POSITIVE LOGITS
    _above
    0.10
    above
    0.10
     precedente
    0.10
     above
    0.09
     diatas
    0.09
    åīįè¿°
    0.09
     acima
    0.09
     précédent
    0.09
    imilar
    0.09
     Above
    0.09
    Activations Density 0.130%

    No Known Activations