© 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. 17204
    Prev
    Next
    INDEX
    Explanations

    whether or not

    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
    ksam
    -0.06
    IMO
    -0.05
    ç«Ł
    -0.05
    W
    -0.05
    abi
    -0.05
    DOG
    -0.05
     impact
    -0.05
    æłĸ
    -0.05
    we
    -0.05
    éĿĴ
    -0.05
    POSITIVE LOGITS
    chine
    0.07
    chin
    0.06
    åŀĭä¼ģä¸ļ
    0.06
    tiva
    0.06
    è¦ģè®¤çľŁ
    0.06
    alous
    0.06
     Berech
    0.06
    GLOSS
    0.06
     jau
    0.06
    åºĶè¿IJ
    0.06
    Activations Density 0.008%

    No Known Activations