© 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. 15594
    Prev
    Next
    INDEX
    Explanations

    intramolecular

    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
    me
    -0.07
    sa
    -0.07
    nowled
    -0.07
    å¶
    -0.06
    dra
    -0.06
    _pd
    -0.06
    .subtract
    -0.06
    sville
    -0.06
    illos
    -0.06
    dale
    -0.06
    POSITIVE LOGITS
    æĪĸå°ij
    0.10
    ally
    0.10
    mente
    0.08
    æ±Łæµ·
    0.08
     felic
    0.07
    /link
    0.07
    çłĶ究表æĺİ
    0.07
    ternal
    0.07
    /local
    0.07
    /self
    0.07
    Activations Density 0.032%

    No Known Activations