© 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. 21988
    Prev
    Next
    INDEX
    Explanations

    script interpreter directives

    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
    s
    -0.06
    Ñĭ
    -0.05
    PP
    -0.05
    éĺ´éĺ³
    -0.05
     memory
    -0.05
    uns
    -0.05
     barring
    -0.05
    ä¸Ģ女
    -0.05
    æ±Łå±±
    -0.05
    .GetInt
    -0.05
    POSITIVE LOGITS
    river
    0.07
    nerg
    0.06
    æ¯Ĥ
    0.06
    åĮºåŁŁç»ıæµİ
    0.06
    çļĦå·¥èµĦ
    0.06
    å°½æľī
    0.06
    ocrin
    0.05
     Algar
    0.05
    elum
    0.05
    =db
    0.05
    Activations Density 0.005%

    No Known Activations