© 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. 21905
    Prev
    Next
    INDEX
    Explanations

    patients

    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
    hie
    -0.06
    èĮĤ
    -0.06
    鬱
    -0.05
    ãģĭãĤīè¦ĭ
    -0.05
    OSC
    -0.05
     sua
    -0.05
    moth
    -0.05
    orsk
    -0.05
    gerak
    -0.05
    æľŁåĨħ
    -0.05
    POSITIVE LOGITS
    ró
    0.06
    ebb
    0.06
    opot
    0.05
    inasikan
    0.05
    erv
    0.05
    -indent
    0.05
    rch
    0.05
     Mich
    0.05
    ãĤ¸ãĥ£
    0.05
     Kushner
    0.05
    Activations Density 0.015%

    No Known Activations