© 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. 22191
    Prev
    Next
    INDEX
    Explanations

    topics or information points

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åºĶçĶ¨
    -0.05
     (
    -0.05
     “
    -0.05
     ‘
    -0.05
    pe
    -0.05
     Element
    -0.05
     staging
    -0.05
    -0.05
    åĨĴ
    -0.04
    **
    -0.04
    POSITIVE LOGITS
    大åı¯
    0.07
    istin
    0.07
     incarcer
    0.06
    ÃŃsk
    0.06
    ä¿¡è¾¾
    0.06
    éĪķ
    0.06
    貨
    0.06
    端åĪ°
    0.06
    icot
    0.06
    eces
    0.06
    Activations Density 0.014%

    No Known Activations