© 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. 19841
    Prev
    Next
    INDEX
    Explanations

    price ranges

    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
    it
    -0.06
    Ùij
    -0.06
    ains
    -0.06
    es
    -0.06
    JM
    -0.06
    umas
    -0.05
    cling
    -0.05
    é¢ł
    -0.05
    en
    -0.05
    old
    -0.05
    POSITIVE LOGITS
    ombok
    0.06
    ICIP
    0.06
    ä¹Łå°±æĺ¯è¯´
    0.06
    lander
    0.05
    ieber
    0.05
    zzi
    0.05
    annonce
    0.05
    IMIT
    0.05
    tori
    0.05
    \_
    0.05
    Activations Density 0.212%

    No Known Activations