© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21360
    Prev
    Next
    INDEX
    Explanations

    years

    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
    æ¶Ī
    -0.06
     جÙĪاÙĨ
    -0.06
     incident
    -0.05
    ail
    -0.05
    ump
    -0.05
    ello
    -0.05
    ret
    -0.05
    ç«ĭ
    -0.05
    elli
    -0.05
    åıį
    -0.05
    POSITIVE LOGITS
    åĪ°çİ°åľ¨
    0.07
    åı£éķĩ
    0.06
    缴åĪ°çİ°åľ¨
    0.06
    estu
    0.06
    åĪ°çĽ®åīį
    0.06
    à¸Ĥà¸ĵะà¸Ļีà¹ī
    0.06
    çİ°ä»»
    0.05
    äºĭåıĺ
    0.05
    æ°ı
    0.05
    çİ°åľ¨æĪij
    0.05
    Activations Density 0.066%

    No Known Activations