© 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. 16832
    Prev
    Next
    INDEX
    Explanations

    insurance premiums and costs

    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
    åī§
    -0.06
    ÑģоÑĢ
    -0.06
    aren
    -0.06
     Krem
    -0.06
    .org
    -0.06
    oros
    -0.06
    ÅĻe
    -0.06
     manca
    -0.05
    æ¶ĪåĮĸçļĦ
    -0.05
    rück
    -0.05
    POSITIVE LOGITS
     probation
    0.06
    erva
    0.06
     profiling
    0.05
    leans
    0.05
    éĿ
    0.05
     callable
    0.05
    循
    0.05
     phạt
    0.05
    æĸ¯åħĭ
    0.05
     impre
    0.05
    Activations Density 0.010%

    No Known Activations