© 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. 63849
    Prev
    Next
    INDEX
    Explanations

    actions and their causes or effects

    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
    xfcr
    -0.07
    artigen
    -0.07
    æĪĸåħ¶ä»ĸ
    -0.07
    å¿«äºĨ
    -0.07
    "/
    -0.07
    lehem
    -0.07
    æ§ĥ
    -0.07
    ilot
    -0.07
    ductive
    -0.06
    æĬĺä¸į
    -0.06
    POSITIVE LOGITS
     infatti
    0.08
     totiž
    0.07
    acu
    0.07
     bowiem
    0.07
    ãģķãģ¦
    0.07
    ftware
    0.07
     indeed
    0.07
     ugyanis
    0.06
    culares
    0.06
     natomiast
    0.06
    Activations Density 0.895%

    No Known Activations