© 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. 19445
    Prev
    Next
    INDEX
    Explanations

    replace new sent delivered free update

    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
    åĽ£
    -0.05
    å²³
    -0.05
    EDGE
    -0.05
     groups
    -0.05
    ram
    -0.05
     meta
    -0.05
    åħ³
    -0.05
    è¶Ĭä½İ
    -0.05
     label
    -0.05
     coherent
    -0.05
    POSITIVE LOGITS
     equ
    0.07
     bénéfic
    0.06
    æ³¢æ¶Ľ
    0.06
     desid
    0.06
     concurrently
    0.06
    otate
    0.06
    ê°Ī
    0.06
     fumar
    0.06
    theless
    0.06
    çijķ
    0.06
    Activations Density 0.011%

    No Known Activations