© 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. 17391
    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
     alist
    -0.06
    éľ
    -0.05
     fq
    -0.05
    igny
    -0.05
    ationship
    -0.05
    виÑĤ
    -0.05
    éĢł
    -0.05
    ÑģÑģе
    -0.05
    æīĢæľīåĨħ容
    -0.05
    æīĢéĢłæĪIJçļĦ
    -0.05
    POSITIVE LOGITS
    é¢Ħç¥Ŀ
    0.05
    ulich
    0.05
    heel
    0.05
    antic
    0.05
    rac
    0.05
    izzi
    0.05
    Einst
    0.05
     заÑīиÑīенÑĭ
    0.05
    rim
    0.05
    ître
    0.05
    Activations Density 0.000%

    No Known Activations