© 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. 20449
    Prev
    Next
    INDEX
    Explanations

    player names or categories

    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
     pe
    -0.06
    peen
    -0.06
    -pe
    -0.06
    åĨ
    -0.06
    iced
    -0.05
    åŁ¹
    -0.05
    çĻ»
    -0.05
    ended
    -0.05
    åıĸ
    -0.05
    udian
    -0.05
    POSITIVE LOGITS
     accepte
    0.06
    spark
    0.05
    类似çļĦ
    0.05
    oro
    0.05
     esqu
    0.05
    Lim
    0.05
    afort
    0.05
     lim
    0.05
    สิà¹īà¸Ļ
    0.05
     emp
    0.05
    Activations Density 0.016%

    No Known Activations