© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18675
    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
    «
    -0.06
    ми
    -0.05
    irim
    -0.05
    è©
    -0.05
    ke
    -0.05
    å°¤åħ¶æĺ¯
    -0.05
    ute
    -0.05
     surroundings
    -0.05
    ä¸ŃæŬ
    -0.05
    ochen
    -0.05
    POSITIVE LOGITS
    -Smith
    0.07
     TERR
    0.07
     lẻ
    0.06
    ipop
    0.06
    Ù°
    0.06
    ciuti
    0.06
     eleg
    0.06
    anze
    0.06
    ,DB
    0.06
    urances
    0.06
    Activations Density 0.000%

    No Known Activations