© 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. 18245
    Prev
    Next
    INDEX
    Explanations

    green acceleration

    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
    çľĭ
    -0.05
    åĭ¤
    -0.05
    ç¥ĸ
    -0.05
    ä¸įæŃ¢
    -0.05
     contraction
    -0.05
     tails
    -0.05
    åĪĨåĪ«
    -0.05
    ä¸Ģæ¦Ĥ
    -0.05
     bre
    -0.04
    opo
    -0.04
    POSITIVE LOGITS
     minuta
    0.06
    çĤ¹å¤ļ
    0.06
    feuer
    0.06
    建æľī
    0.06
    ëį§
    0.06
    ÙĪض
    0.06
    ppen
    0.06
     jau
    0.06
    OOT
    0.06
    xiv
    0.06
    Activations Density 0.030%

    No Known Activations