© 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. 20939
    Prev
    Next
    INDEX
    Explanations

    hybrid systems, recent advances, relative risk

    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
    æĥľ
    -0.05
    ÙĬÙģÙĬØ©
    -0.05
     ...
    -0.05
     pastoral
    -0.05
     cart
    -0.05
    åĽĽå¤Ħ
    -0.05
     ...(
    -0.05
    ...
    -0.05
    è¾
    -0.05
     mates
    -0.05
    POSITIVE LOGITS
    åĽ½å®¶å¯¹
    0.07
    guarded
    0.06
     Ñģобой
    0.06
    ×ķ×ŀר
    0.06
    èĢĥãģĪ
    0.06
    طر
    0.06
    ings
    0.06
    amol
    0.06
     oll
    0.06
    ungan
    0.06
    Activations Density 0.002%

    No Known Activations