© 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. 17840
    Prev
    Next
    INDEX
    Explanations

    numbers, characters, and code fragments

    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
    illy
    -0.06
    emb
    -0.06
    emic
    -0.06
    alam
    -0.06
    çī¹èī²çļĦ
    -0.06
    ART
    -0.06
     alam
    -0.05
     latt
    -0.05
     Ú©Ø´
    -0.05
    rab
    -0.05
    POSITIVE LOGITS
    uite
    0.06
     preci
    0.06
    å±ħ
    0.06
    è¯Ń
    0.05
     satisf
    0.05
     signific
    0.05
    å¼ĥ
    0.05
    anty
    0.05
    eye
    0.05
    rau
    0.05
    Activations Density 0.015%

    No Known Activations