© 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. 21786
    Prev
    Next
    INDEX
    Explanations

    RDD spark context

    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
    yp
    -0.06
    ä¸įæ¸ħ
    -0.06
    alternative
    -0.06
     Alternative
    -0.05
    лÑĮÑĤ
    -0.05
    ager
    -0.05
    udi
    -0.05
    åħ¸èĹı
    -0.05
    èĪĪ
    -0.05
    -mails
    -0.05
    POSITIVE LOGITS
    Anth
    0.06
    æĹłåıį
    0.06
    akens
    0.06
    egos
    0.05
    hek
    0.05
    å·¥çŁ¿
    0.05
     Merc
    0.05
     Anth
    0.05
    åĪĨç±»åı·
    0.05
     anthrop
    0.05
    Activations Density 0.001%

    No Known Activations