© 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. 18349
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

    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
    ↵
    -0.06
    er
    -0.06
    çĮĽåľ°
    -0.05
    P
    -0.05
    PA
    -0.05
    表çİ°å¾Ĺ
    -0.05
    éĢļçĶ¨
    -0.05
    omb
    -0.05
     beloved
    -0.05
    çļĦåį°è±¡
    -0.04
    POSITIVE LOGITS
    à¹Ģหลืà¸Ń
    0.07
    cly
    0.07
    ouble
    0.06
    并讲è¯Ŀ
    0.06
    lett
    0.06
    èī²åĪĹ
    0.06
    avid
    0.06
    ãģ«ãģĶ缸è«ĩ
    0.06
    iate
    0.06
    жиÑĤ
    0.06
    Activations Density 0.022%

    No Known Activations