© 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. 20589
    Prev
    Next
    INDEX
    Explanations

    information related to news

    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
    ielle
    -0.08
    urent
    -0.07
    iona
    -0.07
    æĹ©åīį
    -0.07
    ighbor
    -0.07
    vak
    -0.07
     semb
    -0.07
    зол
    -0.07
     bakar
    -0.06
    çī¹æľĹ
    -0.06
    POSITIVE LOGITS
    0.07
    <
    0.05
    åı¯
    0.05
    èĥľ
    0.05
    侨
    0.05
    åIJĪ
    0.05
    åĸľ
    0.05
     x
    0.05
    T
    0.05
     there
    0.05
    Activations Density 0.001%

    No Known Activations