© 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. 58313
    Prev
    Next
    INDEX
    Explanations

    get followed by method or .php

    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
    ä¸įæĥĬ
    -0.10
    onha
    -0.08
    .cloudflare
    -0.08
    havn
    -0.08
    inality
    -0.08
    faction
    -0.08
    ctions
    -0.08
     полÑĥÑĩеннÑĭÑħ
    -0.08
    elang
    -0.08
    æĸ°åĬłåĿ¡
    -0.07
    POSITIVE LOGITS
    OrCreate
    0.15
    TING
    0.13
    timeofday
    0.12
    tings
    0.11
    ters
    0.11
    ting
    0.10
    PrototypeOf
    0.10
    sockopt
    0.09
     rid
    0.09
    /set
    0.09
    Activations Density 0.092%

    No Known Activations