© 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. 19098
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by location/noun

    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
    érc
    -0.06
    è¿ijäºĽ
    -0.06
    å°ĨæѤ
    -0.06
    .Scheme
    -0.06
    باع
    -0.06
    êter
    -0.06
    被客æĪ·
    -0.06
    ä¿Ĺ
    -0.06
    terne
    -0.06
    andex
    -0.06
    POSITIVE LOGITS
    ho
    0.05
    again
    0.05
    fullscreen
    0.05
     unf
    0.05
    æ¯Ķå¦Ĥ
    0.05
    Sur
    0.05
    èѬå¦Ĥ
    0.05
    opes
    0.05
     Sur
    0.05
    主è¦ģçĶ±
    0.05
    Activations Density 0.016%

    No Known Activations