© 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. 19937
    Prev
    Next
    INDEX
    Explanations

    fitting and training

    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
    大å°Ĩ
    -0.06
    åIJĦç§įåİŁåĽł
    -0.06
    á»Ģ
    -0.06
    edett
    -0.06
    edly
    -0.06
     ÅŁans
    -0.06
    ionen
    -0.06
    liness
    -0.06
    mand
    -0.05
    å¿ĥå¿ĥ
    -0.05
    POSITIVE LOGITS
    orex
    0.06
    -
    0.06
    ãĥŃãĤ°
    0.05
    åIJĮæĹ¶å¯¹
    0.05
    vla
    0.05
     fullest
    0.05
    注è§Ĩ
    0.05
    bserv
    0.05
     digestion
    0.05
    楷
    0.05
    Activations Density 0.002%

    No Known Activations