© 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. 56893
    Prev
    Next
    INDEX
    Explanations

    eta or entity

    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
    er
    -0.11
    nya
    -0.08
    erne
    -0.08
    witz
    -0.08
    herr
    -0.08
    teen
    -0.08
     ëĤĺìĦľ
    -0.08
    ftware
    -0.07
    wich
    -0.07
    cese
    -0.07
    POSITIVE LOGITS
    zelfde
    0.10
    irement
    0.10
    Ø©
    0.10
    aruh
    0.09
    esis
    0.08
    ÑĢоÑģло
    0.08
    macher
    0.08
    ecessary
    0.08
    è£Ķ
    0.08
    ourney
    0.08
    Activations Density 0.011%

    No Known Activations