© 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. 21258
    Prev
    Next
    INDEX
    Explanations

    GB, yards, channel

    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
    ry
    -0.06
    ucs
    -0.05
    agg
    -0.05
    MISS
    -0.05
    uf
    -0.05
    ubo
    -0.05
    arts
    -0.05
    æ»´
    -0.05
    åĢį
    -0.05
    Weapons
    -0.05
    POSITIVE LOGITS
    cum
    0.06
    åľ°ä¹ħ
    0.06
    åĭĩ
    0.05
    /mat
    0.05
     meis
    0.05
    æĮļ
    0.05
    å½°æĺ¾
    0.05
    MAL
    0.05
    åı¥è¯Ŀ说
    0.05
    ÏģεÏħ
    0.05
    Activations Density 0.019%

    No Known Activations