© 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. 18001
    Prev
    Next
    INDEX
    Explanations

    phrases following common parts of words

    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
    awal
    -0.07
    ocen
    -0.06
    obil
    -0.06
    aider
    -0.06
    essin
    -0.06
    voie
    -0.06
    werden
    -0.06
     comps
    -0.06
    descr
    -0.06
    olak
    -0.06
    POSITIVE LOGITS
    nor
    0.05
     nor
    0.05
     necessarily
    0.05
     somehow
    0.05
    大å¸Ī
    0.05
    /
    0.05
    top
    0.05
    Z
    0.04
     allegedly
    0.04
     gross
    0.04
    Activations Density 0.001%

    No Known Activations