© 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. 21854
    Prev
    Next
    INDEX
    Explanations

    .drawImage, Rectangle, bounds

    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
     pencil
    -0.07
     Westbrook
    -0.06
    å°¾
    -0.06
    åĨĻåĪ°
    -0.06
    pha
    -0.06
    opper
    -0.06
    æ·»åĬłåĪ°
    -0.06
    enner
    -0.06
    人
    -0.06
    assage
    -0.06
    POSITIVE LOGITS
    keit
    0.05
    anch
    0.05
    诱
    0.05
    PLEMENT
    0.05
    ello
    0.05
    åħ¶èĩªçĦ¶
    0.05
    ropolit
    0.05
    举åĮĹ
    0.05
     anch
    0.05
     gar
    0.05
    Activations Density 0.001%

    No Known Activations