© 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. 12684
    Prev
    Next
    INDEX
    Explanations

    condensation

    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
    hood
    -0.10
    fulness
    -0.09
    éļĪ
    -0.09
    ories
    -0.09
    enticate
    -0.08
    ê¾¼
    -0.08
    er
    -0.07
    å¾ij
    -0.07
    -0.07
    cing
    -0.07
    POSITIVE LOGITS
    ensation
    0.11
    lobber
    0.09
    urah
    0.09
    ensed
    0.08
    ularity
    0.08
    urso
    0.08
    æľīèĩ´
    0.08
    uplic
    0.08
    aneous
    0.08
    ebene
    0.08
    Activations Density 0.019%

    No Known Activations