© 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. 19866
    Prev
    Next
    INDEX
    Explanations

    0

    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
    bridge
    -0.05
    æĬĢæľ¯æĸ¹æ¡Ī
    -0.05
    tings
    -0.05
    static
    -0.05
     prototypes
    -0.05
    quence
    -0.05
    quad
    -0.05
    æ¯ĶåĪ©
    -0.05
    ä¸ĢåĬ¨
    -0.05
     Static
    -0.05
    POSITIVE LOGITS
     simulate
    0.06
    åĽŀãĤĬ
    0.06
    Ñĩками
    0.06
     uj
    0.06
    awy
    0.06
    åĭĻ
    0.06
    çªĿéĩĮ
    0.06
    alah
    0.06
     simulated
    0.06
    baran
    0.06
    Activations Density 0.151%

    No Known Activations