© 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. 22252
    Prev
    Next
    INDEX
    Explanations

    reinstall or regenerate

    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
    bedingt
    -0.06
    ä¸ĭä¸Ģç¯ĩ
    -0.06
    uppe
    -0.05
    è¿
    -0.05
    å¤ļ头
    -0.05
    å¤ļåıij
    -0.05
    å¤ļ亩
    -0.05
    .next
    -0.05
    éªĩ
    -0.05
    andel
    -0.05
    POSITIVE LOGITS
     utr
    0.06
     Maur
    0.06
    als
    0.06
    atr
    0.06
    repo
    0.06
    rain
    0.05
    Ñĩе
    0.05
    örd
    0.05
    -Pro
    0.05
    bo
    0.05
    Activations Density 0.009%

    No Known Activations