© 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. 20787
    Prev
    Next
    INDEX
    Explanations

    fourth wall crashing

    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
    phies
    -0.05
    éļ
    -0.05
    cpf
    -0.05
    åľ¨ä¸Ĭ
    -0.05
    uide
    -0.05
    éħĿéħ¿
    -0.05
    onse
    -0.05
    è¡į
    -0.05
     оз
    -0.05
    èµ°åİ»
    -0.05
    POSITIVE LOGITS
    大æĸ¹
    0.07
    áh
    0.06
     reader
    0.06
    æĿijéĩĮçļĦ
    0.06
    æķ¦
    0.06
    reader
    0.06
     anale
    0.06
     frontale
    0.06
    icare
    0.06
    attle
    0.05
    Activations Density 0.005%

    No Known Activations