© 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. 17173
    Prev
    Next
    INDEX
    Explanations

    solve for

    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
    inkan
    -0.07
     solving
    -0.07
    ofd
    -0.07
    EAU
    -0.06
    éĤ¦
    -0.06
    åı°ä¸ĬçļĦ
    -0.06
    illes
    -0.06
    epsi
    -0.06
    解åĨ³æĸ¹æ³ķ
    -0.06
    rozum
    -0.06
    POSITIVE LOGITS
    ermo
    0.05
    genommen
    0.05
    rost
    0.05
     Colon
    0.05
     demais
    0.05
    ievo
    0.05
    足
    0.05
    并åıĸå¾Ĺ
    0.05
    MED
    0.05
    usch
    0.05
    Activations Density 0.008%

    No Known Activations