© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20858
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    U
    -0.05
    äºĭ
    -0.05
    S
    -0.05
    -0.05
    许
    -0.05
     well
    -0.05
    -s
    -0.05
    ex
    -0.05
    å®ļ
    -0.05
    I
    -0.05
    POSITIVE LOGITS
    BOT
    0.07
     spok
    0.07
    mö
    0.07
    alas
    0.07
     disipl
    0.07
    örde
    0.07
    inken
    0.07
     ÑģÑİда
    0.06
    adop
    0.06
    inks
    0.06
    Activations Density 0.000%

    No Known Activations