© 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. 17732
    Prev
    Next
    INDEX
    Explanations

    powershell script | batch file

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ufr
    -0.08
    untung
    -0.07
     charisma
    -0.07
    idane
    -0.07
    wykle
    -0.07
    keyp
    -0.07
    ingk
    -0.07
    mented
    -0.07
    éĽĨåħ¨
    -0.07
    regor
    -0.07
    POSITIVE LOGITS
    *
    0.05
    var
    0.05
    0.05
     en
    0.05
     over
    0.05
     Var
    0.05
     haz
    0.05
     opinion
    0.05
    èŀįåIJĪ
    0.04
     me
    0.04
    Activations Density 0.002%

    No Known Activations