© 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. 21013
    Prev
    Next
    INDEX
    Explanations

    how and was questions

    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
     Pike
    -0.06
    acaks
    -0.06
    écr
    -0.06
     uncert
    -0.06
    å¾·åįİ
    -0.06
     porad
    -0.06
    éĥ¨çº§
    -0.06
     psychology
    -0.06
    ationer
    -0.06
     Soros
    -0.06
    POSITIVE LOGITS
     ob
    0.06
    Overrides
    0.05
     en
    0.05
    äºĮèĢħ
    0.05
     dign
    0.05
     o
    0.05
    0.05
    äºİä¸Ģ
    0.05
     âĢ¦
    0.05
    arc
    0.05
    Activations Density 0.001%

    No Known Activations