© 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. 17008
    Prev
    Next
    INDEX
    Explanations

    start or begin a process

    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
    erci
    -0.06
    åħ¬å¹³åħ¬æŃ£
    -0.06
    æĶ¯éĥ¨ä¹¦è®°
    -0.06
     annonc
    -0.06
    stad
    -0.06
    openh
    -0.05
    çľĭ好çļĦ
    -0.05
    iszt
    -0.05
    ç½ijåıĭè¯Ħ论
    -0.05
    rade
    -0.05
    POSITIVE LOGITS
    rush
    0.06
    Ùģر
    0.05
    设æ³ķ
    0.05
    èĨľ
    0.05
    大çļĦ
    0.05
    aniem
    0.05
    teilung
    0.05
     tangible
    0.05
    建工
    0.05
    adier
    0.05
    Activations Density 0.016%

    No Known Activations