© 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. 17015
    Prev
    Next
    INDEX
    Explanations

    C2, Morrison, SYLVESTER, Thule, mango, Krampus

    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
     consci
    -0.07
    ROUP
    -0.06
    δη
    -0.06
    posé
    -0.06
     Polis
    -0.06
    esel
    -0.06
    Ñİ
    -0.06
    olec
    -0.06
    éĵ
    -0.06
    iode
    -0.06
    POSITIVE LOGITS
    ·¸
    0.06
    an
    0.06
    STA
    0.05
    หลวà¸ĩ
    0.05
     Dakota
    0.05
    ine
    0.05
    ued
    0.05
    orado
    0.05
    orsch
    0.05
    ded
    0.05
    Activations Density 0.013%

    No Known Activations