© 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. 17749
    Prev
    Next
    INDEX
    Explanations

    directions and locations

    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
    OGRAPH
    -0.07
    æĻ°
    -0.06
    woods
    -0.06
    ASURE
    -0.06
    asts
    -0.06
     **.**
    -0.06
    åĮ»çĶŁå»ºè®®
    -0.06
     اÙĦØ£ÙĪ
    -0.06
     اÙĦباÙĦ
    -0.06
    gek
    -0.06
    POSITIVE LOGITS
     b
    0.05
    ç¿»
    0.05
    ep
    0.05
    b
    0.05
    re
    0.05
    ead
    0.05
    说æľī
    0.05
     Egyptian
    0.05
    eb
    0.05
    DA
    0.04
    Activations Density 0.001%

    No Known Activations