© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16753
    Prev
    Next
    INDEX
    Explanations

    "is there" followed by a or any

    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
    Negative Logits
    åıĪ
    -0.05
    æĮ
    -0.05
     Sands
    -0.05
    еÑģÑģ
    -0.05
     Perez
    -0.05
    çĭĻ
    -0.05
     Bremer
    -0.05
    ÑĩаÑģ
    -0.05
    ULD
    -0.05
    endor
    -0.05
    POSITIVE LOGITS
    ENDER
    0.06
    yes
    0.06
    aduras
    0.05
    avern
    0.05
    utt
    0.05
    缸åħ³åĨħ容
    0.05
    atea
    0.05
    æĪ¿
    0.05
    Ñħоде
    0.05
    odal
    0.05
    Activations Density 0.033%

    No Known Activations