© 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. 20592
    Prev
    Next
    INDEX
    Explanations

    numbers followed by descriptive units

    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
    uling
    -0.07
    leven
    -0.06
    antin
    -0.06
     اÙĦأعÙĦÙī
    -0.06
    ifax
    -0.06
    меÑĩа
    -0.06
    dalena
    -0.05
    èĬ±å²Ĺ
    -0.05
    çIJĨçļĦ
    -0.05
    ôle
    -0.05
    POSITIVE LOGITS
     rein
    0.05
     REPLACE
    0.05
     biá»ĩt
    0.05
    es
    0.05
    ÛĮÙĨ
    0.05
    лÑĸ
    0.05
     them
    0.05
    Ñĸн
    0.05
     modern
    0.05
    并åıĬæŶ
    0.05
    Activations Density 0.007%

    No Known Activations