© 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. 21403
    Prev
    Next
    INDEX
    Explanations

    timer or script tags

    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
    .or
    -0.07
    ouce
    -0.06
    runde
    -0.06
    apore
    -0.06
    orr
    -0.05
    ^K
    -0.05
    '),('
    -0.05
    æĪIJç«ł
    -0.05
     dentro
    -0.05
    bane
    -0.05
    POSITIVE LOGITS
    igh
    0.06
    éĽĨçļĦ
    0.06
     tro
    0.05
    åįģåħ¨
    0.05
    é»
    0.05
     ev
    0.05
    comb
    0.05
    çĶ
    0.05
    åĩ«
    0.05
     Ñĥго
    0.05
    Activations Density 0.096%

    No Known Activations