© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20752
    Prev
    Next
    INDEX
    Explanations

    end of sentences, good luck!

    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
    /
    -0.05
    via
    -0.05
     via
    -0.05
    å¤Ħäºİ
    -0.05
    åĺ¶
    -0.04
    ane
    -0.04
    avin
    -0.04
    è¿Ļæĺ¯æĪij们
    -0.04
    åIJĪæ³ķæĿĥçĽĬ
    -0.04
    æĭĴä¸į
    -0.04
    POSITIVE LOGITS
    ÑĤÑĸм
    0.06
    ê²Į
    0.06
    borg
    0.06
    å°Ķ
    0.06
    diag
    0.06
    gether
    0.06
    éĿŀæłĩ
    0.06
     οÏĢοί
    0.06
    icidad
    0.06
    วิà¸Īารà¸ĵà¹Į
    0.06
    Activations Density 0.012%

    No Known Activations