© 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. 17581
    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
    olle
    -0.07
    alent
    -0.06
    гл
    -0.06
    riot
    -0.06
    clinic
    -0.06
    alma
    -0.06
    rib
    -0.06
    oule
    -0.06
     двига
    -0.06
    ç®
    -0.06
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.06
    ród
    0.05
    umb
    0.05
    åĪ°å¤Ħéĥ½æĺ¯
    0.05
    ä¸ŃçļĦ
    0.05
    go
    0.05
     factors
    0.05
    Into
    0.05
    ÎŃ
    0.05
     Compte
    0.05
    Activations Density 0.000%

    No Known Activations