© 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. 22203
    Prev
    Next
    INDEX
    Explanations

    outcome of competition

    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
     interrom
    -0.07
     revient
    -0.06
    çĥŃçĤ¹
    -0.06
     sez
    -0.06
    çĽIJåĴĮ
    -0.06
    èĦīæIJı
    -0.06
    人åķĬ
    -0.06
     Zas
    -0.06
    åĬ«
    -0.06
    live
    -0.06
    POSITIVE LOGITS
    emo
    0.06
    oste
    0.05
    im
    0.05
    дне
    0.05
    -selector
    0.05
    oun
    0.05
    imb
    0.05
    éłĺ
    0.05
    çł¥çłºåīįè¡Į
    0.05
     factor
    0.04
    Activations Density 0.016%

    No Known Activations