© 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. 17748
    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
    èĮ¬
    -0.06
    URRE
    -0.05
    étant
    -0.05
    æĿ¥è¯´
    -0.05
    è¶Ĭæĺ¯
    -0.05
    ä¾Ĩ說
    -0.05
    对äºİä¸Ģ个
    -0.05
    碰
    -0.05
    .RelativeLayout
    -0.05
    ä¸įä½ľä¸º
    -0.05
    POSITIVE LOGITS
    up
    0.07
     componentDidUpdate
    0.06
    å½ķ
    0.06
    angelo
    0.06
     dolar
    0.05
    eq
    0.05
    åĨħ
    0.05
    åħ±
    0.05
    upon
    0.05
    along
    0.05
    Activations Density 0.000%

    No Known Activations