© 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. 17718
    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
    åĥıåľ¨
    -0.06
    åĥı
    -0.06
    alink
    -0.05
     global
    -0.05
     лиÑĪениÑı
    -0.05
    ersen
    -0.05
    åĨį次
    -0.05
    world
    -0.05
    ro
    -0.05
    to
    -0.05
    POSITIVE LOGITS
     داÙħ
    0.07
     pitching
    0.06
    ÎŃÏĤ
    0.06
    angkutan
    0.06
     explan
    0.06
     muka
    0.06
    ç¡®æľī
    0.06
    دÙĩ
    0.06
    ÙĤÙħ
    0.06
    ç¾¹
    0.06
    Activations Density 0.000%

    No Known Activations