© 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. 22033
    Prev
    Next
    INDEX
    Explanations

    ON followed by table/column names

    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
     préal
    -0.08
    elas
    -0.07
    those
    -0.07
    onav
    -0.06
    onte
    -0.06
    å¾Īæ·±
    -0.06
    akon
    -0.06
    kolwiek
    -0.06
     aquelas
    -0.06
    交æĺĵä¼ļ
    -0.06
    POSITIVE LOGITS
    0.06
     Jr
    0.06
     (
    0.06
    ly
    0.05
    å®ļçļĦ
    0.05
    lim
    0.05
     +
    0.05
    /downloads
    0.05
    ting
    0.04
    cc
    0.04
    Activations Density 0.002%

    No Known Activations