© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18574
    Prev
    Next
    INDEX
    Explanations

    Venus, ABC, BIG, PG

    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
    ,
    -0.05
    好好çļĦ
    -0.05
    w
    -0.05
    -0.05
     look
    -0.05
    ึ
    -0.04
    ama
    -0.04
    c
    -0.04
    äºĮä¸ī
    -0.04
    .
    -0.04
    POSITIVE LOGITS
     *–
    0.10
     ÑĥÑģпе
    0.07
    rowable
    0.07
    Ñģловно
    0.07
    ç»Ħç»ĩèĢħ
    0.07
    benh
    0.06
    zie
    0.06
    пÑĢоÑĩем
    0.06
    pit
    0.06
     Loot
    0.06
    Activations Density 0.248%

    No Known Activations