© 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. 18180
    Prev
    Next
    INDEX
    Explanations

    null or nil values

    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
    rhein
    -0.07
    szer
    -0.06
    åĽłèĢĮ
    -0.06
    anita
    -0.06
    ìķ¼
    -0.06
    íķľ
    -0.06
     Insomma
    -0.06
     dér
    -0.06
    å¾Ĺè¦ģ
    -0.06
    ocation
    -0.06
    POSITIVE LOGITS
    awang
    0.05
    пÑĭ
    0.05
    اش
    0.05
    lis
    0.05
    ÑĩÑĭ
    0.05
    archy
    0.05
    w
    0.05
    ÏĤ
    0.05
    lk
    0.05
     L
    0.05
    Activations Density 0.006%

    No Known Activations