© 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. 18456
    Prev
    Next
    INDEX
    Explanations

    particle, tubing, flow, packets

    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
     premi
    -0.07
    Ñĩке
    -0.06
    转载æĪĸå¼ķçĶ¨
    -0.06
    çĻĸ
    -0.06
    ille
    -0.06
    rames
    -0.06
    äsche
    -0.06
    综åIJĪåĪĨæŀIJ
    -0.06
    èī¯å¤ļ
    -0.06
    -outs
    -0.06
    POSITIVE LOGITS
     att
    0.05
     process
    0.05
    å´İ
    0.05
    身ä¸ĬçļĦ
    0.05
    ãĢģ“
    0.05
    åIJ«æľī
    0.05
    æĢĢ
    0.05
    inom
    0.05
    i
    0.05
    带çĿĢ
    0.05
    Activations Density 0.031%

    No Known Activations