© 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. 21631
    Prev
    Next
    INDEX
    Explanations

    to followed by a verb

    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
    ure
    -0.07
     ÑģÑħод
    -0.06
    ä¹ĭæĻĤ
    -0.06
    å©ķ
    -0.06
    æĺ±
    -0.06
    cion
    -0.06
    serie
    -0.06
    nap
    -0.06
    rape
    -0.06
    navbarSupportedContent
    -0.05
    POSITIVE LOGITS
    çĦ¶å¤§
    0.07
    an
    0.07
    anine
    0.06
    aná
    0.06
    ä¸įçĦ¶
    0.06
    er
    0.06
     Hav
    0.06
    lings
    0.06
    éĥİ
    0.06
    manship
    0.05
    Activations Density 0.027%

    No Known Activations