© 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. 19969
    Prev
    Next
    INDEX
    Explanations

    ed, inated, reactions, cent, izing

    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
    resco
    -0.06
     discr
    -0.06
    褪èī²
    -0.05
    "..
    -0.05
    unte
    -0.05
    orsa
    -0.05
    embalikan
    -0.05
    poke
    -0.05
    anak
    -0.05
    nier
    -0.05
    POSITIVE LOGITS
    ä¸ĢåĢį
    0.06
     PLUS
    0.06
    latih
    0.05
    bout
    0.05
    aur
    0.05
    opic
    0.05
     капиÑĤала
    0.05
    è¿ĻèĪ¬
    0.05
     their
    0.05
    opl
    0.05
    Activations Density 0.001%

    No Known Activations