© 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. 21481
    Prev
    Next
    INDEX
    Explanations

    Odds ratios, hazard ratios, risk

    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
    æĽ²çº¿
    -0.05
     fract
    -0.05
    ems
    -0.05
    صØŃ
    -0.05
    ianto
    -0.04
     cav
    -0.04
     consol
    -0.04
    ache
    -0.04
    çĽ´çº¿
    -0.04
    oug
    -0.04
    POSITIVE LOGITS
    åĩłçİĩ
    0.07
     Odds
    0.07
    erma
    0.07
    æĻļä¸ĬçļĦ
    0.06
     Nus
    0.06
     Qaeda
    0.06
     Chance
    0.06
    æĹłå¤Ħ
    0.06
    è¯ķçĶ¨
    0.06
    éĮł
    0.06
    Activations Density 0.245%

    No Known Activations