© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19541
    Prev
    Next
    INDEX
    Explanations

    prior to

    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
    es
    -0.06
    ات
    -0.06
    s
    -0.06
    äºĽ
    -0.05
     dá»įa
    -0.05
    ห
    -0.05
     g
    -0.05
    ëģĶ
    -0.05
    -0.05
    ŀ
    -0.05
    POSITIVE LOGITS
    portun
    0.10
    edul
    0.08
    ÑģÑĤеÑģÑĤвенно
    0.08
    vrier
    0.08
    hon
    0.08
    irez
    0.07
    cpt
    0.07
    å¹´åģĩ
    0.07
    isial
    0.07
    设å¤ĩçŃī
    0.07
    Activations Density 0.021%

    No Known Activations