© 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. 19014
    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
    immel
    -0.07
    som
    -0.07
     pupper
    -0.07
    vij
    -0.07
    avn
    -0.07
    оÑģÑĥ
    -0.06
    ujan
    -0.06
    øv
    -0.06
    Referensi
    -0.06
    asonry
    -0.06
    POSITIVE LOGITS
    çŁ¥åħ¶
    0.06
     Bi
    0.06
    èĤ¡
    0.05
     ins
    0.05
     P
    0.05
    hec
    0.05
     bi
    0.05
     A
    0.05
    被
    0.05
    åħ·
    0.05
    Activations Density 0.000%

    No Known Activations