© 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. 64422
    Prev
    Next
    INDEX
    Explanations

    accumulation or deposits

    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
    ĮĢ
    -0.08
    åĶ
    -0.07
     lift
    -0.07
     дем
    -0.07
     momentan
    -0.07
    .setCharacter
    -0.07
     Lus
    -0.07
     momentarily
    -0.07
    ilag
    -0.07
     ucwords
    -0.07
    POSITIVE LOGITS
     accumulation
    0.10
    æ²ī积
    0.09
    积累
    0.09
     accumulating
    0.09
     accumulated
    0.09
     accum
    0.08
    积累äºĨ
    0.08
    积累çļĦ
    0.08
    è·Ŀä»Ĭ
    0.08
     deposits
    0.08
    Activations Density 0.005%

    No Known Activations