© 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. 17096
    Prev
    Next
    INDEX
    Explanations

    fear, animal fear, citations

    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
    enis
    -0.06
    Âł
    -0.05
    i
    -0.05
    èĽ¤
    -0.05
    ijo
    -0.05
    é¸
    -0.05
    ³³
    -0.05
    èĻļ
    -0.05
    æĶ¿çŃĸæĢ§
    -0.05
    arani
    -0.05
    POSITIVE LOGITS
     Ortega
    0.06
     Whip
    0.06
    odge
    0.06
    orest
    0.06
    igsaw
    0.06
    inz
    0.06
    ctic
    0.06
    tron
    0.06
    ddy
    0.06
     perch
    0.06
    Activations Density 0.003%

    No Known Activations