© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20490
    Prev
    Next
    INDEX
    Explanations

    information provided

    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
    меÑĩа
    -0.09
    ëį°ìļĶ
    -0.09
     desconhe
    -0.08
    eworthy
    -0.08
     tenden
    -0.08
    ucho
    -0.08
    oczes
    -0.08
    Ñĥжи
    -0.08
    efeld
    -0.08
    ulement
    -0.08
    POSITIVE LOGITS
    0.08
    ,
    0.07
     on
    0.07
     (
    0.07
    1
    0.07
     l
    0.06
    .
    0.06
    ↵
    0.06
    2
    0.05
     /
    0.05
    Activations Density 0.005%

    No Known Activations