© 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. 18482
    Prev
    Next
    INDEX
    Explanations

    file path, file name

    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
    为己
    -0.07
    ingo
    -0.06
    alley
    -0.06
    اء
    -0.06
    eyer
    -0.06
    å¤ł
    -0.06
    uil
    -0.06
    orld
    -0.06
    lein
    -0.06
    èĩ³åħ³
    -0.06
    POSITIVE LOGITS
    gether
    0.08
    ness
    0.07
    ation
    0.07
    sono
    0.06
    Ø©
    0.06
    ÑĢÑĮ
    0.06
    ameran
    0.06
    ored
    0.05
    sss
    0.05
    ieÃŁ
    0.05
    Activations Density 0.004%

    No Known Activations