© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16573
    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
    Negative Logits
    ther
    -0.05
    ax
    -0.05
    åIJĪå½±çķĻ念
    -0.05
    ät
    -0.05
    otel
    -0.05
    thing
    -0.05
     amenaza
    -0.05
     termination
    -0.05
    èı²çī¹
    -0.04
     concepts
    -0.04
    POSITIVE LOGITS
    kring
    0.06
    å®ļäºĨ
    0.06
    临
    0.06
    ediat
    0.06
    Ñĥнк
    0.06
    identi
    0.06
    lane
    0.06
    idium
    0.06
    æĦ¿
    0.06
    idin
    0.06
    Activations Density 0.000%

    No Known Activations