© 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. 18113
    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
    åºĶæīĭ
    -0.07
    éŀį
    -0.06
    oeff
    -0.06
    iltr
    -0.06
    Constructed
    -0.06
    issé
    -0.06
    举åįĩ
    -0.06
    ä¸Ģæī«
    -0.06
    ervi
    -0.06
    å§Ĩæĸ¯
    -0.06
    POSITIVE LOGITS
     bec
    0.05
    arka
    0.05
    çĿĢäºĨ
    0.05
    itu
    0.05
    bec
    0.05
    //=
    0.05
    åĵªä½į
    0.05
    ECA
    0.05
    ële
    0.05
    liga
    0.04
    Activations Density 0.000%

    No Known Activations