© 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. 18363
    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
     ch
    -0.06
     salv
    -0.05
     spp
    -0.05
     those
    -0.05
     d
    -0.05
     há»ĵi
    -0.05
    å±¥
    -0.05
     scal
    -0.05
    isar
    -0.04
    those
    -0.04
    POSITIVE LOGITS
    opin
    0.08
    vaard
    0.07
    olos
    0.07
    ä¸ĩäºĭ
    0.07
    agin
    0.07
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    0.07
    veill
    0.06
    åı¦
    0.06
     associaz
    0.06
    æĥ³çľĭ
    0.06
    Activations Density 0.012%

    No Known Activations