© 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. 16574
    Prev
    Next
    INDEX
    Explanations

    decoding or decoder

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    illa
    -0.06
    imes
    -0.06
    iless
    -0.06
    iare
    -0.06
    isc
    -0.06
    rez
    -0.05
     genug
    -0.05
    好å¤Ħ
    -0.05
    ally
    -0.05
    asuk
    -0.05
    POSITIVE LOGITS
    cles
    0.06
    ters
    0.06
    agram
    0.06
    venta
    0.06
    adder
    0.06
    گر
    0.06
    omen
    0.06
    è±ģ
    0.06
    ation
    0.06
    ched
    0.05
    Activations Density 0.009%

    No Known Activations