© 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. 17185
    Prev
    Next
    INDEX
    Explanations

    solidified, hardened, set

    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
    iable
    -0.06
     cạn
    -0.06
    rary
    -0.06
    rape
    -0.06
    iless
    -0.06
    ezu
    -0.06
    缴åĪ°
    -0.06
    kota
    -0.06
    usat
    -0.06
     اÙĦØŃض
    -0.05
    POSITIVE LOGITS
    ÙĪا
    0.06
     within
    0.06
    ë§ĪìŀIJ
    0.05
    ara
    0.05
    orte
    0.05
     creatively
    0.05
    çŃ¾
    0.05
    使çĶ¨æĿĥ
    0.05
    اØŃ
    0.05
     Gew
    0.05
    Activations Density 0.001%

    No Known Activations