© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18945
    Prev
    Next
    INDEX
    Explanations

    puppeteer.launch

    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
    好æŃ¹
    -0.05
    Navig
    -0.05
     navig
    -0.05
    दि
    -0.05
    itasi
    -0.05
    _mon
    -0.05
    å¾Ĺèµ·
    -0.05
     Navig
    -0.05
     Lamar
    -0.05
    ông
    -0.05
    POSITIVE LOGITS
    cule
    0.06
    ÑĦии
    0.06
    çĶ«
    0.06
     Acomp
    0.06
    глÑĥ
    0.06
    undef
    0.06
    Õ¸ÖĤÕ©
    0.06
    ombra
    0.06
    åħīçݯ
    0.06
    åĸĺæģ¯
    0.06
    Activations Density 0.005%

    No Known Activations