© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16800
    Prev
    Next
    INDEX
    Explanations

    git and docker commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    zinho
    -0.07
    ippo
    -0.07
    afil
    -0.06
    èĬĿ
    -0.06
    常
    -0.06
    filt
    -0.06
    gil
    -0.06
    ndern
    -0.06
    HOUSE
    -0.06
    ovre
    -0.06
    POSITIVE LOGITS
     ref
    0.05
     life
    0.05
    åĶ¾
    0.05
     vac
    0.05
    wick
    0.05
    olia
    0.05
    éľĢè¦ģåıĬæŶ
    0.05
    é¾
    0.04
     undergone
    0.04
     enfr
    0.04
    Activations Density 0.009%

    No Known Activations