© 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. 20146
    Prev
    Next
    INDEX
    Explanations

    targeting and treatments

    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
    Locked
    -0.06
    å¹³åĿĩåĪĨ
    -0.06
    urn
    -0.06
    stories
    -0.06
     sez
    -0.06
    æĺİ示
    -0.06
    imb
    -0.05
     Locked
    -0.05
    anno
    -0.05
     вед
    -0.05
    POSITIVE LOGITS
     scattering
    0.06
    è²ī
    0.05
     Vie
    0.05
    åİ¢
    0.05
    sy
    0.05
     spreading
    0.05
    æ°ĹãģĮ
    0.05
    åºķæ°Ķ
    0.05
     ìĤ¬ìĿ´
    0.05
    itas
    0.05
    Activations Density 0.011%

    No Known Activations