© 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. 21952
    Prev
    Next
    INDEX
    Explanations

    allow your

    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
    åīįèĦ¸
    -0.06
    åĴĮåŁ¹åħ»
    -0.05
    occa
    -0.05
    åŁºç¡ĢæĢ§
    -0.05
    herits
    -0.05
    okies
    -0.05
    ya
    -0.05
    ÙĨدÙĩ
    -0.05
     bek
    -0.05
    achu
    -0.05
    POSITIVE LOGITS
    bon
    0.06
    éľĦ
    0.05
    æĥħ
    0.05
    æĪĪ
    0.05
    itos
    0.05
    Dictionary
    0.05
    è¯įæ±ĩ
    0.05
    ÏĦά
    0.05
    ardan
    0.05
    æį®æѤ
    0.05
    Activations Density 0.039%

    No Known Activations