© 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. 20851
    Prev
    Next
    INDEX
    Explanations

    locations followed by context

    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
    ardon
    -0.06
    NER
    -0.06
    éĶĻ
    -0.05
    ieder
    -0.05
    anz
    -0.05
    anne
    -0.05
    vertisement
    -0.05
    ä¸įå®ļ
    -0.05
    icum
    -0.05
    à¸Ńà¸Ķ
    -0.05
    POSITIVE LOGITS
     -,
    0.06
     Bret
    0.06
    çļĦåħ¨éĥ¨åĨħ容
    0.05
    ','-
    0.05
    æ³¢åħī
    0.05
    IFF
    0.05
    acier
    0.05
     alone
    0.05
    裡çļĦ
    0.05
    ']}'
    0.05
    Activations Density 0.109%

    No Known Activations