© 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. 20760
    Prev
    Next
    INDEX
    Explanations

    observing specimens

    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
    reff
    -0.06
    å¥ĹçĶ¨
    -0.05
    ottes
    -0.05
    ì§ĢìĤ¬
    -0.05
    born
    -0.05
    .azure
    -0.05
    åľ¨åįĬ
    -0.05
    ck
    -0.05
    otte
    -0.05
    使çĶ¨è¯¥
    -0.05
    POSITIVE LOGITS
    reator
    0.07
    asia
    0.06
    jang
    0.06
     natür
    0.06
    eloos
    0.05
    æĿIJæĸĻçļĦ
    0.05
    祥
    0.05
    大åħ¬
    0.05
    éģĵçļĦ
    0.05
    纳
    0.05
    Activations Density 0.311%

    No Known Activations