© 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. 21485
    Prev
    Next
    INDEX
    Explanations

    Alien Gang

    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
    å®ķ
    -0.06
    ivre
    -0.06
    å½ĵ好
    -0.06
    ibra
    -0.05
    uros
    -0.05
    æĺ¥æĹ¥
    -0.05
    estre
    -0.05
    æĸĻçļĦ
    -0.05
     misd
    -0.05
    nius
    -0.05
    POSITIVE LOGITS
    az
    0.06
    azan
    0.06
     az
    0.06
    ucs
    0.06
    antina
    0.05
    éĶ¦
    0.05
    åijľ
    0.05
    ics
    0.05
    asan
    0.05
    аз
    0.05
    Activations Density 0.001%

    No Known Activations