© 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. 18714
    Prev
    Next
    INDEX
    Explanations

    divide, merge, border, gap concepts

    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
    éĢIJ
    -0.06
    ukum
    -0.06
    czyk
    -0.06
    èĮ²
    -0.06
    ounce
    -0.06
    碰
    -0.05
    ุà¸Ķ
    -0.05
     suite
    -0.05
    zew
    -0.05
    ocom
    -0.05
    POSITIVE LOGITS
    çķĮéĻIJ
    0.09
    ä¸įåĪĨ
    0.08
     distinctions
    0.07
     distinction
    0.07
     merging
    0.06
    å®ļä¹ī
    0.06
     merges
    0.06
     blending
    0.06
     borders
    0.06
    labels
    0.06
    Activations Density 0.057%

    No Known Activations