© 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. 21564
    Prev
    Next
    INDEX
    Explanations

    when/if clauses

    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®Įä¹ĭåIJİ
    -0.06
    =?
    -0.06
    æĮģ
    -0.06
    ahnya
    -0.06
    utures
    -0.06
     disso
    -0.06
    ueb
    -0.05
    好åIJİ
    -0.05
    æľºæŀª
    -0.05
    éĥ¨ãģ®
    -0.05
    POSITIVE LOGITS
    ÑģÑĤÑĮ
    0.06
    ä¸Ģæĭį
    0.06
    ست
    0.05
    转转
    0.05
    коло
    0.05
    è©
    0.05
    Tap
    0.05
     characteristic
    0.05
    nell
    0.05
    нин
    0.05
    Activations Density 0.001%

    No Known Activations