© 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. 18218
    Prev
    Next
    INDEX
    Explanations

    *list markers and subsequent concepts

    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
    اصÙĦ
    -0.06
    è¡Įä¹ĭ
    -0.06
    麽
    -0.05
    tom
    -0.05
    .sig
    -0.05
     OTHERWISE
    -0.05
    aporte
    -0.05
    нÑĨа
    -0.05
    åĩº
    -0.05
    驹
    -0.05
    POSITIVE LOGITS
    непÑĢо
    0.06
    å¦ĤåĽł
    0.06
    olini
    0.06
    åľ°éĹ®éģĵ
    0.05
     tergantung
    0.05
     indire
    0.05
    éĢīæĭ©éĢĤåIJĪèĩªå·±çļĦ
    0.05
    æĿijéĩĮçļĦ
    0.05
     Coh
    0.05
     Wonder
    0.05
    Activations Density 0.004%

    No Known Activations