© 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. 18073
    Prev
    Next
    INDEX
    Explanations

    URLs and domain 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
    jung
    -0.07
    вленное
    -0.07
    ufer
    -0.06
    UserProfile
    -0.06
    agan
    -0.06
    raje
    -0.06
    fighter
    -0.06
    spre
    -0.06
    esor
    -0.06
     heng
    -0.06
    POSITIVE LOGITS
    èĢĹ
    0.05
    tsel
    0.05
     Citation
    0.05
    PP
    0.05
    ensivo
    0.05
     dol
    0.05
    çĶŁåij½çº¿
    0.05
    রা
    0.05
    çıĢ
    0.05
    ity
    0.05
    Activations Density 0.077%

    No Known Activations