© 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. 19038
    Prev
    Next
    INDEX
    Explanations

    license, copyright, or contribution

    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
    kans
    -0.07
    знаÑĩа
    -0.07
     HOWEVER
    -0.06
     íĸĪê³ł
    -0.06
     alco
    -0.06
    波波
    -0.06
    äumt
    -0.06
    zog
    -0.06
    ãĤĵãģ°ãĤĵ
    -0.06
    ORG
    -0.06
    POSITIVE LOGITS
     te
    0.06
     thereof
    0.06
    缸åºĶ
    0.06
     accordingly
    0.05
    缸åºĶçļĦ
    0.05
     All
    0.05
     S
    0.05
    ed
    0.05
    ä¹IJäºİ
    0.05
     A
    0.04
    Activations Density 0.011%

    No Known Activations